Conceptio › Archive › Google Patents

Google Patentsopen access

Secure machine learning analytics using homomorphic encryption — Enveil, Inc. (US11902413B2)

Enveil, Inc. · Google Patents

Google Patents · Patents · License: Open Access

Open Source ↗

ellisonannewilliams enveil

patent, google patents, intellectual property, US11902413B2, Enveil, Inc., Ellison Anne Williams, en, 2024

ABSTRACT

Abstract

Provided are methods and systems for performing a secure machine learning analysis over an instance of data. An example method includes acquiring, by a client, a homomorphic encryption scheme, and at least one machine learning model data structure. The method further includes generating, using the encryption scheme, at least one homomorphically encrypted data structure, and sending the encrypted data structure to at least one server. The method includes executing a machine learning model, by the at least one server based on the encrypted data structure to obtain an encrypted result. The method further includes sending, by the server, the encrypted result to the client where the encrypted result is decrypted. The machine learning model includes neural networks and decision trees.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is a continuation of U.S. Non-Provisional application Ser. No. 16/803,718, filed on Feb. 27, 2020, which claims the benefit and priority of U.S. Non-Provisional Application Ser. No. 15/876,024, filed on Jan. 19, 2018, which claims the benefit and priority of U.S. Provisional Application Ser. No. 62/448,890, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,918, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,893, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,906, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,908, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,913, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,916, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,883, filed on Jan. 20, 2017; U.S. Provisional Application 62/448,885, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,902, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,896, filed on Jan. 20, 2017; U.S. Provisional Application Ser. No. 62/448,899, filed on Jan. 20, 2017; and U.S. Provisional Application Ser. No. 62/462,818, filed on Feb. 23, 2017; all of which are hereby incorporated by reference herein, including all references and appendices, for all purposes.

TECHNICAL FIELD

This disclosure relates to the technical field of encryption and decryption of data. More specifically, this disclosure relates to systems and methods for performing secure analytics using a homomorphic encryption including analytics for machine learning models.

Advantageously, a homomorphic encrypted analytic can execute on a server in an unsecure environment and there by obfuscate information about the analytic that could be derived by examination of the analytic. This information could include the information about computation being performed, intellectual property, proprietary information, sensitive information, or protected classes of information. Specifically, the analytics include trained machine learning models, sent in a homomorphic encrypted scheme, and executed in an unsecure environment. Thereby, the encrypted analytic can be sent to an untrusted environment, be evaluated against data under the untrusted party's control, and generate an encrypted prediction, classification or other result which can be transmitted back to a trusted environment. The decrypted result will be the same as if the unencrypted machine analytic operated on the data.

BACKGROUND

With development of computer technologies, many sensitive data, such as financial information and medical records can be kept on remote servers or cloud-based computing resources. Authorized users can access the sensitive data using applications running, for example, on their personal computing devices. Typically, personal computing devices are connected, via data networks, to servers or cloud-based computing resources. Therefore, the sensitive data can be subject to unauthorized access.

Encryption techniques, such as a homomorphic encryption, can be applied to the sensitive data to prevent unauthorized access. The encryption techniques can be used to protect âdata in useâ, âdata in restâ, and âdata in transitâ. A homomorphic encryption is a form of encryption in which a specific algebraic operation (generally referred to as addition or multiplication) performed on plaintext, is equivalent to another operation performed on ciphertext. For example, in Partially Homomorphic Encryption (PHE) schemes, multiplication in ciphertext is equal to addition of the same values in plaintext.

SUMMARY

This summary is provided to introduce a selection of concepts in a simplified form that are further described in the Detailed Description below. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

Generally, the present disclosure is directed to the technology for secure data processing. Some embodiments of the present disclosure may facilitate a secure transmission of machine learning models from a client device to remote computing resource(s) for performing trained machine learning models over an instance(s) of data and secure transmission of results of the analysis from the computing resources back to the client device. These analytics include machine learning models including but not limited to neural network models and decision tree models where the generated results can be securely transmitted back to a client device.

According to one example embodiment of the present disclosure, a method for performing secure machine learning models using homomorphic encryption is provided. The method may include receiving, from a client, by at least one server from a client, at least one machine learning data structure. The at least one machine learning data structure can be encrypted using a homomorphic encryption scheme. The method may further include extracting, by the at least one server, an instance wherein an instance includes but is not limited to data, derived analytic results, and results of a term generator. The method may further include evaluating, by the at least one server, the at least one machine learning data structure over the instance utilizing a trained machine learning model to obtain at least one encrypted result. The method may further allow sending, by the at least one server, the at least one encrypted result to the client, wherein the client is configured to decrypt the at least one encrypted result using the homomorphic encryption scheme.

In some embodiments, the homomorphic encryption scheme includes a fully homomorphic encryption scheme. The fully homomorphic encryption scheme may include at least one of a Brakerski/Fan-Vercauteren and a Cheon-Kim-Kim-Song cryptosystem.

In some embodiments, the at least one machine learning data structure is generated based on an associated trained machine learning model. The encrypted value can be obtained using the homomorphic encryption scheme.

In certain embodiments, the machine learning model is a neural network. The at least one machine learning data structure includes neural network weights associated with the neural network.

In other embodiments, the machine learning model includes a decision tree. The at least one machine learning data structure includes a feature vector. In various embodiments, the feature vectors are binary values.

According to one example embodiment of the present disclosure, a system for performing a secure machine learning model results using homomorphic encryption is provided. The system may include at least one processor and a memory storing processor-executable codes, wherein the at least one processor can be configured to implement the operations of the above-mentioned method for performing secure analytics using homomorphic encryption.

According to yet another example embodiment of the present disclosure, the operations of the above-mentioned method for performing secure analytics using a homomorphic encryption are stored on a machine-readable medium comprising instructions, which when implemented by one or more processors perform the recited operations.

Other example embodiments of the disclosure and aspects will become apparent from the following description taken in conjunction with the following drawings.

BRIEF DESCRIPTION OF DRAWINGS

Exemplary embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements.

FIG. 1 is a block diagram of an example environment suitable for practicing methods for secure analytics using a homomorphic encryption as described herein.

FIG. 2 is a block diagram showing details of a homomorphic encryption scheme, according to an example embodiment.

FIG. 3 is a flow chart of an example method for performing secure analytics using a homomorphic encryption.

FIG. 4 is a computer system that can be used to implement some embodiments of the present disclosure.

FIG. 5 is a block diagram of an example environment suitable for practicing methods for secure machine learning models using a homomorphic encryption as described herein.

FIG. 6 a is a diagram of an artificial neuron.

FIG. 6 b is a diagram of an artificial neuron with encrypted weights.

FIG. 7 is a graph of an activation function.

FIG. 8 a is a decision tree with yes/no nodes.

FIG. 8 b is an encrypted decision tree.

FIG. 9 is a diagram showing details of a decision tree homomorphic encryption scheme, according to an example embodiment.

FIG. 10 is a flow chart of an example method for performing secure machine learning models using homomorphic encryption.

DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS

The technology disclosed herein is concerned with methods and systems for performing secure analytics over data source using a homomorphic encryption. Embodiments of the present disclosure may facilitate a secure transmission of analytics from a client device to computing resource(s) providing a target data source and secure transmission of results of analytics from the computing resource(s) back to the client device.

Some embodiments of the present disclosure may be used to encrypt an analytic on a client device using homomorphic encryption techniques. The encrypted analytic can be sent to computing resource(s) providing desired data source(s). The encrypted analytics can be performed over desired data source(s) to produce encrypted results. The encrypted results can be returned to the client device and decrypted using the homomorphic encryption techniques. Embodiments of the present disclosure may allow performing of an analytic over desired data sources in a secure and private manner because neither content of the analytic nor results of the analytic are revealed to a data owner, observer, or attacker.

According to one example embodiment of the present disclosure, a method for performing secure analytics using a homomorphic encryption may commence with acquiring, by a client, an analytic, at least one analytic parameter associated with the analytic, and an encryption scheme. The encryption scheme may include a public key for encryption and a private key for decryption. The method may further include generating, by the client and using the encryption scheme, at least one analytical vector based on the analytic and the at least one analytic parameter. The method may further include sending, by the client, the at least one analytical vector and the encryption scheme, to at least one server.

The method may also include acquiring, by the at least one server, a data set for performing the analytic. The method may allow extracting, by the at least one server and based on the encryption scheme, a set of terms from the data set. The method may further include, evaluating, by the at least one server, the at least one analytical vector over the set of terms to obtain at least one encrypted result. The method may also include sending, by the at least one server, the at least one encrypted result to the client. The method may also include decrypting, by the client and based on the encryption scheme, the at least one encrypted result to generate at least one result of the analytic.

In other embodiments, the analytics can include ML (machine learning) models executing on a server resident or coupled instance in a non-trusted environment. An instance includes but is not limited to data, derived analytic results, and the result of a term generator. ML models are an extension to the encrypted analytics. The ML models can take different forms depending upon the particular machine learning algorithm being used. However, in all cases they contain data structures, including but not limited to vectors of weights for a neural network or a tree of features and splits for a decision tree. The data structures are used by the ML models to generate a result about a previously unseen instance of a problem. Like models, results and instances can take different forms depending on the use case. For example, an instance could be a picture and the result could be a classification of the picture as âcontains a faceâ or âdoes not contain a face;â or an instance could be the historical prices for a stock over the past year and the result could be the price of that stock in three months.

Alternatively, the analytics may not be as complicated as a training machine learning model for a neural network or a decision tree. The ML analytics can include computing a histogram, an average, or executing a regression modeling calculating a result based on the data.

A ML model may be created using a training algorithm, whose input is a large number of instances called âtraining data.â The training algorithm is run over this training data to fill in the data structure that constitutes the ML model, in such a way that the model makes good predictions, classifications, or other results over the instances in the training data. Once the ML model training is complete, the finished ML model, including the trained data structures, can be saved and used to make predictions, classifications, or other results against new instances of data encountered in the future. This saved ML model can also be executed by other parties, who can use the ML model to make predictions about instances they encounter.

Transmitting to or otherwise sharing the ML model with other parties carries risks, because it is possible to learn about the ML model by studying the data structures and data coefficients that comprise the ML model. For many ML models, a âmodel inversion attackâ can be used to reconstruct some of the training data from the ML model. If that training data contained sensitive information, this attack can expose training data to unauthorized parties. Many ML models are also susceptible to âadversarial machine learningâ techniques, which study the decision-making process represented by the ML model and look for ways to âfoolâ the ML model into making a bad result for some new instance. Further, many organizations consider their trained ML models to be proprietary information.

The disclosed systems and methods include techniques for using homomorphic encryption to encrypt parts of an already-trained ML (machine learning) model. Such systems and methods protects against the attacks described above by denying the attacker the ability to analyze the contents of the model as well as exposure of the model itself which may be considered proprietary. The disclosed systems and methods replaces the standard operations used during analysis with homomorphic operations, which makes it possible to use the encrypted ML model to generate encrypted results about new instances. The encrypted results can be transferred to a trusted or secure environment for decryption using a compatible homomorphic encryption model, and the ML model owner can decide whether to keep the result private or share it with the other parties. Below are two examples of how this invention can be used to homomorphically encrypt two types of machine learning models: a neural network and a decision tree.

CROSS-REFERENCE TO RELATED APPLICATIONS

TECHNICAL FIELD

BACKGROUND

SUMMARY

In certain embodiments, the machine learning model is a neural network. The at least one machine learning data structure includes neural network weights associated with the neural network.

Other example embodiments of the disclosure and aspects will become apparent from the following description taken in conjunction with the following drawings.

BRIEF DESCRIPTION OF DRAWINGS

Exemplary embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements.

FIG. 1 is a block diagram of an example environment suitable for practicing methods for secure analytics using a homomorphic encryption as described herein.

FIG. 2 is a block diagram showing details of a homomorphic encryption scheme, according to an example embodiment.

FIG. 3 is a flow chart of an example method for performing secure analytics using a homomorphic encryption.

FIG. 4 is a computer system that can be used to implement some embodiments of the present disclosure.

FIG. 5 is a block diagram of an example environment suitable for practicing methods for secure machine learning models using a homomorphic encryption as described herein.

FIG. 6 a is a diagram of an artificial neuron.

FIG. 6 b is a diagram of an artificial neuron with encrypted weights.

FIG. 7 is a graph of an activation function.

FIG. 8 a is a decision tree with yes/no nodes.

FIG. 8 b is an encrypted decision tree.

FIG. 9 is a diagram showing details of a decision tree homomorphic encryption scheme, according to an example embodiment.

FIG. 10 is a flow chart of an example method for performing secure machine learning models using homomorphic encryption.

DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS

Referring now to the drawings, various embodiments are described in which like reference numerals represent like parts and assemblies throughout the several views. It should be noted that the reference to various embodiments does not limit the scope of the claims attached hereto. Additionally, any examples outlined in this specification are not intended to be limiting and merely set forth some of the many possible embodiments for the appended claims.

FIG. 1 shows a block diagram of an example environment 100 suitable for practicing the methods described herein. It should be noted, however, that the environment 100 is just one example and is a simplified embodiment provided for illustrative purposes, and reasonable deviations of this embodiment are possible as will be evident for those skilled in the art.

As shown in FIG. 1 , the environment 100 may include at least one client device 105 (also referred to as a client 105 ) and at least one server 110 . The client(s) 105 can include any appropriate computing device having network functionalities allowing the device to communicate to server(s) 110 . In some embodiments, the client(s) 105 can be connected to the server(s) 110 via one or more wired or wireless communications networks. In various embodiments, the client(s) 105 includes, but is not limited to, a computer (e.g., laptop computer, tablet computer, desktop computer), a server, cellular phone, smart phone, gaming console, multimedia system, smart television device, set-top box, infotainment system, in-vehicle computing device, informational kiosk, smart home computer, software application, computer operating system, modem, router, and so forth. In some embodiments, the client(s) 105 can be used by users for Internet browsing purposes.

In some embodiments, the server(s) 110 may be configured to store or provide access to at least one data source(s) 115 . In certain embodiments, the server(s) 110 may include a standalone computing device. In various embodiments, the data source(s) 115 may be located on a single server(s) 110 or distributed over multiple server(s) 110 . The data source(s) 115 may include plaintext data, deterministically encrypted data, semantically encrypted data, or a combination of thereof.

In some embodiments, the server(s) 110 may be implemented as cloud-based computing resource shared by multiple users. The cloud-based computing resource(s) can include hardware and software available at a remote location and accessible over a network (for example, the Internet). The cloud-based computing resource(s) can be dynamically re-allocated based on demand. The cloud-based computing resources may include one or more server farms/clusters including a collection of computer servers which can be co-located with network switches and/or routers.

In various embodiments, the client(s) 105 can make certain client inquires within the environment 100 . For example, the client(s) 105 may be configured to send analytics to the server(s) 110 to be performed over the data source(s) 115 . The server(s) 110 can be configured to perform the analytics over the data source(s) 115 and return the results of analytics to the client(s) 105 .

To protect the content of the analytics, the client(s) 105 can be configured to encrypt the analytics using a homomorphic encryption scheme. The homomorphic encryption scheme can include a partially homomorphic encryption scheme and fully homomorphic encryption scheme. The partially homomorphic encryption scheme can include one of a Rivest, Shamir and Adleman cryptosystem, Elgamal cryptosystem, Benaloh cryptosystem, Goldwasser-Micali cryptosystem, and Pallier cryptosystem. The analytics can be encrypted with a public (encryption) key of the homomorphic encryption scheme. The encrypted analytics and the public key can be sent to the server 110 . The encrypted analytics can be only decrypted with a private (decryption) key of the homomorphic encryption scheme. The decryption key can be kept on the client(s) 105 and never provided to the server(s) 110 .

To protect the content of the results of the analytic, the server(s) 110 can be further configured to perform the encrypted analytics on the data source using the same homographic encryption scheme and the public key received from the client 105 and, thereby, obtain encrypted results of the analytics. The encrypted results can be sent to the client(s) 105 . The client(s) 105 can decrypt the encrypted results using the private key. Because the private key is always kept on the client(s) 105 , neither encrypted analytic nor encrypted results of the analytics can be decrypted on the server 110 or when intercepted while in transition between the client(s) 105 and the server(s) 110 .

FIG. 2 is a block diagram showing details of homomorphic encryption scheme 200 , according to some example embodiments. The modules of the scheme 200 can be implemented as software instructions stored in memory of the client 105 and executed by at least one processor of the client 105 . The client 105 may be configured to acquire a desired analytic A to be executed over data source 115 . The analytic A can be associated with analytic parameter set {A_P}. The analytic A and analytic parameter set {A_P} can be further encrypted into a sequence of homomorphic analytical vectors {A_V} using a homomorphic encryption scheme E.

The scheme 200 may include a term generation (TG) function 210 . The term generation function 210 can be used to extract a set of term elements {T} of analytic A that correspond to an analytic parameter A_P. For, example, if the analytic parameter A_P is a frequency distribution for database elements in <row:column> pairs where row=Y, then the set {T} reflects the frequency distribution of these elements from the database.

The scheme 200 may further include a keyed hash function H(T) 220 . The hash function H(T) can be used to obtain a set H(T)={H(T): T in {T}}. The set H(T) is the range of the hash function H(T) over the set of term elements {T}. The keyed hash function H(T) can be associated with a public key used for the encryption. The number of distinct elements in the set H(T) is equal to the number of distinct elements in the set of term elements {T}.

The scheme 200 may further include an analytical vector construction module 230 . The module 230 can be used to construct an analytical vector A_V for the analytic parameter A_P. The desired size s of the analytical vector A_V can be selected to be greater than the number of distinct elements in the set of term elements {T}. For index j=0, . . . , (sâ1): if H(T)=j for a term element T in the set {T}, then vector component A_V[j]=E(B_j) where B_j is a nonzero bit mask corresponding to the term element T, wherein E is the homographic encryption scheme. If there is no T in {T} such that H(T)=j, then A_V[j]=E(0). In this manner, the analytical vector A_V includes encryptions of nonzero bitmasks for only the term elements present in the set {T}. The analytic A cannot be recovered from the analytical vectors {A_V} without a private key associated with the homomorphic encryption scheme E.

The client(s) 105 can be further configured to send the analytical vectors {A_V}, the term generation function TG, and the hash function H(T) with the public key to the server(s) 110 .

In some embodiments, the server(s) 110 can be configured to extract a set of term elements {T} from the data source(s) 115 using the term generation function TG and the keyed hash function H(T). The server(s) 110 can be further configured to evaluate the encrypted analytical vectors {A_V} over the set of term elements {T} to produce encrypted results E(R). The server(s) 110 can be further configured to send the encrypted results E(R) to the client 105 .

The client 105 can be configured to decrypt the encrypted results E(R) in order to obtain the results R using the private key of the homomorphic encryption scheme E. Because the analytical vector {A_V} includes nonzero entries for terms in set {T}, the homomorphic properties of E ensure that only results corresponding to the nonzero elements of the analytical vector {A_V} are present in results R.

FIG. 3 is a flow chart of an example method 300 for performing secure analytics using a homomorphic encryption, according to some example embodiments. The method 300 may be performed within environment 100 illustrated in FIG. 1 . Notably, the steps recited below may be implemented in an order different than described and shown in the FIG. 3 . Moreover, the method 300 may have additional steps not shown herein, but which can be evident to those skilled in the art from the present disclosure. The method 300 may also have fewer steps than outlined below and shown in FIG. 3 .

The method 300 may commence in block 305 with receiving, by at least one server, from a client, at least one analytic vector, a term generation function, and a keyed hash function. The at least one analytic vector can be encrypted using the homomorphic encryption scheme. The homomorphic encryption scheme can include a public key for encryption and a private key for decryption.

In block 310 , the method 300 may proceed with extracting, by the at least one server, a set of term components from a data set using the term generation function and the keyed hashed function.

In block 315 , the method 300 may evaluate, by the at least one server, the at least one analytic vector over the set of term components to obtain at least one encrypted result.

In block 320 , the method may proceed with sending, by the at least one server, the at least one encrypted result to the client. The client can be configured to decrypt the at least one encrypted result using the homomorphic encryption scheme.

FIG. 4 illustrates an exemplary computer system 400 that may be used to implement some embodiments of the present disclosure. The computer system 400 of FIG. 4 may be implemented in the contexts of the likes of the client 105 , the server(s) 110 , and the data source 115 . The computer system 400 of FIG. 4 includes one or more processor units 410 and main memory 420 . Main memory 420 stores, in part, instructions and data for execution by processor units 410 . Main memory 420 stores the executable code when in operation, in this example. The computer system 400 of FIG. 4 further includes a mass data storage 430 , portable storage device 440 , output devices 450 , user input devices 460 , a graphics display system 470 , and peripheral devices 480 .

The components shown in FIG. 4 are depicted as being connected via a single bus 490 . The components may be connected through one or more data transport means. Processor unit 410 and main memory 420 is connected via a local microprocessor bus, and the mass data storage 430 , peripheral device(s) 480 , portable storage device 440 , and graphics display system 470 are connected via one or more input/output (I/O) buses.

Mass data storage 430 , which can be implemented with a magnetic disk drive, solid state drive, or an optical disk drive, is a non-volatile storage device for storing data and instructions for use by processor unit 410 . Mass data storage 430 stores the system software for implementing embodiments of the present disclosure for purposes of loading that software into main memory 420 .

Portable storage device 440 operates in conjunction with a portable non-volatile storage medium, such as a flash drive, floppy disk, compact disk, digital video disc, or Universal Serial Bus (USB) storage device, to input and output data and code to and from the computer system 400 of FIG. 4 . The system software for implementing embodiments of the present disclosure is stored on such a portable medium and input to the computer system 400 via the portable storage device 440 .

User input devices 460 can provide a portion of a user interface. User input devices 460 may include one or more microphones, an alphanumeric keypad, such as a keyboard, for inputting alphanumeric and other information, or a pointing device, such as a mouse, a trackball, stylus, or cursor direction keys. User input devices 460 can also include a touchscreen. Additionally, the computer system 400 as shown in FIG. 4 includes output devices 450 . Suitable output devices 450 include speakers, printers, network interfaces, and monitors.

Graphics display system 470 include a liquid crystal display (LCD) or other suitable display device. Graphics display system 470 is configurable to receive textual and graphical information and processes the information for output to the display device.

Peripheral devices 480 may include any type of computer support device to add additional functionality to the computer system.

The components provided in the computer system 400 of FIG. 4 are those typically found in computer systems that may be suitable for use with embodiments of the present disclosure and are intended to represent a broad category of such computer components that are well known in the art. Thus, the computer system 400 of FIG. 4 can be a personal computer (PC), hand held computer system, telephone, mobile computer system, workstation, tablet, phablet, mobile phone, server, minicomputer, mainframe computer, wearable, or any other computer system. The computer may also include different bus configurations, networked platforms, multi-processor platforms, and the like. Various operating systems may be used including UNIX, LINUX, WINDOWS, MAC OS, PALM OS, QNX ANDROID, IOS, CHROME, TIZEN, and other suitable operating systems.

The processing for various embodiments may be implemented in software that is cloud-based. In some embodiments, the computer system 400 is implemented as a cloud-based computing environment, such as a virtual machine operating within a computing cloud. In other embodiments, the computer system 400 may itself include a cloud-based computing environment, where the functionalities of the computer system 400 are executed in a distributed fashion. Thus, the computer system 400 , when configured as a computing cloud, may include pluralities of computing devices in various forms, as will be described in greater detail below.

In general, a cloud-based computing environment is a resource that typically combines the computational power of a large grouping of processors (such as within web servers) and/or that combines the storage capacity of a large grouping of computer memories or storage devices. Systems that provide cloud-based resources may be utilized exclusively by their owners or such systems may be accessible to outside users who deploy applications within the computing infrastructure to obtain the benefit of large computational or storage resources.

The cloud may be formed, for example, by a network of web servers that comprise a plurality of computing devices, such as the computer system 400 , with each server (or at least a plurality thereof) providing processor and/or storage resources. These servers may manage workloads provided by multiple users (e.g., cloud resource customers or other users). Typically, each user places workload demands upon the cloud that vary in real-time, sometimes dramatically. The nature and extent of these variations typically depends on the type of business associated with the user.

FIG. 5 shows a block diagram of an example environment 500 suitable for practicing the ML methods described herein. It should be noted, however, that the environment 500 is just one example and is a simplified embodiment provided for illustrative purposes, and reasonable deviations of this embodiment are possible as will be evident for those skilled in the art.

As shown in FIG. 5 , the environment 500 can include at least one client device 510 (also referred to as a client 510 ) and at least one server 520 . As shown, the client(s) 510 can operate in a secure or trusted environment. The client(s) 510 can include any appropriate computing device having network functionalities allowing the device to communicate to server(s) 520 . In some embodiments, the client(s) 510 can be connected to the server(s) 520 via one or more wired or wireless communications networks. In various embodiments, the client(s) 510 includes, but is not limited to, a computer (e.g., laptop computer, tablet computer, desktop computer), a server, cellular phone, smart phone, gaming console, multimedia system, smart television device, set-top box, infotainment system, in-vehicle computing device, informational kiosk, smart home computer, software application, computer operating system, modem, router, and so forth. While these various embodiments can include all these client devices, beneficially the client operates in a trusted environment and that the use of the client(s) 510 and the ML analytics or ML analytic data structures or parameters sent therefrom and results received are protected from unauthorized users.

The server(s) 520 can operate in an untrusted environment where an unencrypted machine analytic could be evaluated to learn information about computation being performed, intellectual property, proprietary information, sensitive information, or protected classes of information about ML analytic or the result of the ML analytic operation on instance(s) 530 . For the purpose of this disclosure, an instance(s) 530 is input data used by a trained ML analytic to make a prediction, classification, or generate another result. The server(s) 520 receives homomorphically encrypted data structures 516 associated with a trained ML analytic, and executed in the homomorphically encrypted scheme. Thus, information about the ML analytic is obfuscated from parties in the untrusted environment.

In some embodiments, the server(s) 520 may be configured to store or provide access to at least one instance(s) 530 . In certain embodiments, the server(s) 520 may include a standalone computing device. In various embodiments, the instance(s) 530 may be located on a single server(s) 520 or distributed over multiple server(s) 520 . The instance(s) 530 may include plaintext data.

In some embodiments, the server(s) 520 may be implemented as cloud-based computing resource shared by multiple users. The cloud-based computing resource(s) can include hardware and software available at a remote location and accessible over a network (for example, the Internet). The cloud-based computing resource(s) can be dynamically re-allocated based on demand. The cloud-based computing resources may include one or more server farms/clusters including a collection of computer servers which can be co-located with network switches and/or routers.

In various embodiments, the client(s) 510 can make certain client inquires within the environment 500 . For example, the client(s) 510 may be configured to send ML analytics to the server(s) 520 to be performed over the instance(s) 530 . The server(s) 520 can be configured to perform the ML analytics over the instance (s) 530 and return the results of ML analytics to the client(s) 510 .

To protect the content of the ML analytics, the client(s) 510 can include a ML analytics module(s) 512 that include at least one ML analytic model. These models can include but are not limited to neural networks models, decision tree models, or regression analysis models. These ML analytics models can be represented as machine executable code or using other representations including higher level languages.

The ML analytics contain at least one ML analytic data structure. These include data structures such as vectors of weights for a neural network analytic or a data structure representing a tree of features and splits for a decision tree analytic. The weight vector W n represents the trained weights for the neural network. More details regarding the neural network is provided below. For the ML decision tree, the associated data structure is the pre-specified tree of features and splits.

The trained weights W n of the neural network or data structure for the decision tree vector is passed to the HED (Homomorphic Encryption/Decryption) module 514 . This module encrypts the ML analytic data structure using a homomorphic encryption scheme. In one embodiment, a fully homomorphic encryption scheme is used including but not limited to BFV (Brakerski/Fan-Vercauteren) and CKKS (Cheon-Kim-Kim-Song). Details of the homomorphic encryption of a trained neural network and decision tree data structures are described in more detail below.

The HED module 514 receives at least one data structure from the ML analytics module 512 . The HED module 514 can also receive the ML analytic for transmission to the server(s) 520 or alternatively the servers(s) 520 can be preloaded with the ML analytic but lacking the trained data structures. The HED module 514 homomorphically encrypts the ML analytic data structure 516 which is transmitted to the server(s) 520 .

The HED model 514 is configured to receive the homomorphically encrypted result 524 , decrypt the result 524 using the homomorphic scheme, and output a result 518 .

To protect previously mentioned aspects of a ML analytic, the server(s) 520 can be configured to perform the ML analytics using the ML homomorphically encrypted data structures in a homomorphic scheme on the instances 530 and thereby, obtain encrypted result of the encrypted ML analytics 522 . The encrypted result 524 can be sent to the client(s) 510 . The HED 514 can decrypt the ML encrypted result generating an unencrypted result 518 .

Homomorphically Encrypted Neural Network Analytics

FIG. 6 a shows a neuron 600 that may be used in a neural network analytic. A neural network is a type of machine learning model that is loosely modeled on the behavior of neurons and synapses in the brain. A neural network consists of a number of artificial neurons 600 , arranged into a series of âlayers.â Each artificial neuron can have input 610 and output connections 640 , along which they receive and transmit âsignals,â which are real number values. Each artificial neuron also has an âactivation function,â 630 which is a mathematical function that determines what the neuron's output signals will be given its input signals. Output O

1 640 is one output of a single layer system. Each connection is also assigned a âweight,â 620 which is multiplied with the signal 610 to determine the inputs to the activation function 630 . The weight 620 is a measure of the importance of the signal in determining the neuron's output 640 .

To make a result based on an instance, real values extracted from the instance are fed into the neural network as inputs 610 along designated input connections to the first layer of artificial neurons. These <figure-callout id="610" label="inputs" filenames="US11902413-

CLAIMS

Claims ( 20 )

What is claimed is:

1. A method for performing a secure machine learning analysis using homomorphic encryption, the method comprising:

the machine learning data structure including at least one feature vector having a feature depth that is greater than a decision depth of the decision tree machine learning model,

the machine learning data structure based on the trained decision tree machine learning model;

extracting, by the at least one server, a previously unseen instance of data;

evaluating, by the at least one server, the encrypted machine learning data structure over the previously unseen instance of data using the decision treemachine learning model containing the encrypted machine learning data structure to generate at least one encrypted result about the previously unseen instance of data; and

sending, from the at least one server, the at least one encrypted result to the client, the at least one encrypted result configured to be decrypted at the client using the homomorphic encryption scheme.

2. The method of claim 1 , wherein the homomorphic encryption scheme includes a fully homomorphic encryption scheme.

3. The method of claim 2 , wherein the fully homomorphic encryption scheme includes at least one of a Brakerski/Fan-Vercauteren and a Cheon-Kim-Kim-Song cryptosystem.

4. The method of claim 1 , wherein the trained decision tree machine learning model is a regression model.

5. The method of claim 1 , wherein the at least one feature vector consists of binary values.

6. A system for performing a secure machine learning analysis in an environment using homomorphic encryption, the system comprising:

at least one processor in an environment; and

a memory communicatively coupled with the at least one processor, the memory storing instructions, which when executed by the at least processor perform a method comprising:

receiving, from a client, by at least one server in the environment, an encrypted machine learning data structure formed by using a homomorphic encryption scheme to encrypt a machine learning data structure that has been generated by training a decision tree machine learning model that contains the machine learning data structure, the training performed in a trusted environment,

the machine learning data structure including at least one feature vector having a feature depth that is greater than a decision depth of the decision tree machine learning model,

the machine learning data structure based on the trained decision tree machine learning model;

extracting, by the at least one server, a previously unseen instance of data;

evaluating, by the at least one server, the encrypted machine learning data structure over the previously unseen instance of data using the decision tree machine learning model containing the encrypted machine learning data structure to generate at least one encrypted result about the previously unseen instance of data; and

7. The system of claim 6 , wherein the homomorphic encryption scheme includes a fully homomorphic encryption scheme.

8. The system of claim 7 , wherein the homomorphic encryption scheme includes at least one of a Brakerski/Fan-Vercauteren and a Cheon-Kim-Kim-Song cryptosystem.

9. The system of claim 6 , wherein the at least one feature vector consists of binary values.

10. The system of claim 6 , wherein the trained decision tree machine learning model is a regression model.

11. A non-transitory computer-readable storage medium having embodied thereon instructions, which when executed by at least one processor, perform steps of a method, the method comprising:

receiving, from a client, by at least one server in an environment, an encrypted machine learning data structure formed by using a homomorphic encryption scheme to encrypt a machine learning data structure that has been generated by training a machine learning model that contains the machine learning data structure, the training performed in a trusted environment, the trained machine learning model being a decision tree that has a decision depth, the encrypted machine learning data structure including at least one feature vector having a feature depth that is greater than the decision depth of the trained machine learning model, the machine learning data structure based on the trained machine learning model;

extracting, by the at least one server, a previously unseen instance of data;

evaluating, by the at least one server, the encrypted machine learning data structure over the previously unseen instance of data using the machine learning model containing the encrypted machine learning data structure to generate at least one encrypted result about the previously unseen instance of data; and

12. The non-transitory computer-readable storage medium of claim 11 , wherein the homomorphic encryption scheme includes a fully homomorphic encryption scheme.

13. The non-transitory computer-readable storage medium of claim 12 , wherein the fully homomorphic encryption scheme includes at least one of a Brakerski/Fan-Vercauteren and a Cheon-Kim-Kim-Song cryptosystem.

14. The non-transitory computer-readable storage medium of claim 11 , wherein the at least one feature vector consists of binary values.

15. The non-transitory computer-readable storage medium of claim 11 , wherein the trained machine learning model is a regression model.

16. A method for performing a secure machine learning analysis using homomorphic encryption, the method comprising:

the neural network machine learning model including a feature vector having a decision depth and a feature vector having a feature depth that is greater than the decision depth,

the machine learning data structure based on the trained neural network machine learning model;

extracting, by the at least one server, a previously unseen instance of data;

evaluating, by the at least one server, the encrypted at least one machine learning data structure over the previously unseen instance of data using the neural network machine learning model containing the encrypted machine learning data structure of the neural network machine learning model to generate at least one encrypted result about the previously unseen instance of data; and

17. The method of claim 16 , wherein the homomorphic encryption scheme includes a fully homomorphic encryption scheme.

18. The method of claim 17 , wherein the homomorphic encryption scheme includes at least one of a Brakerski/Fan-Vercauteren and a Cheon-Kim-Kim-Song cryptosystem.

19. The method of claim 16 , wherein the feature vector consists of binary values.

20. The method of claim 16 , wherein the trained neural network machine learning model is a regression model.

US17/473,778

2017-01-20

2021-09-13

Secure machine learning analytics using homomorphic encryption

Active

2038-02-07

US11902413B2

( en )

Priority Applications (2)

Application Number

Priority Date

Filing Date

Title

US17/473,778

US11902413B2

( en )

2017-01-20

2021-09-13

Secure machine learning analytics using homomorphic encryption

US18/525,378

US20240113858A1

( en )

2017-01-20

2023-11-30

Systems and Methods for Performing Secure Machine Learning Analytics Using Homomorphic Encryption

Applications Claiming Priority (16)

Application Number

Priority Date

Filing Date

Title

US201762448908P

2017-01-20

US201762448918P

2017-01-20

US201762448893P

2017-01-20

US201762448885P

2017-01-20

US201762448913P

2017-01-20

US201762448896P

2017-01-20

US201762448899P

2017-01-20

US201762448883P

2017-01-20

US201762448902P

2017-01-20

US201762448890P

2017-01-20

US201762448916P

2017-01-20

US201762448906P

2017-01-20

US201762462818P

2017-02-23

US15/876,024

US10644876B2

( en )

2017-01-20

2018-01-19

Secure analytics using homomorphic encryption

US16/803,718

US11196541B2

( en )

2017-01-20

2020-02-27

Secure machine learning analytics using homomorphic encryption

US17/473,778

US11902413B2

( en )

2017-01-20

2021-09-13

Secure machine learning analytics using homomorphic encryption

Related Parent Applications (1)

Application Number

Title

Priority Date

Filing Date

US16/803,718

Continuation

US11196541B2

( en )

2017-01-20

2020-02-27

Secure machine learning analytics using homomorphic encryption

Related Child Applications (1)

Application Number

Title

Priority Date

Filing Date

US18/525,378

Continuation

US20240113858A1

( en )

2017-01-20

2023-11-30

Systems and Methods for Performing Secure Machine Learning Analytics Using Homomorphic Encryption

Publications (2)

Publication Number

Publication Date

US20210409191A1

US20210409191A1 ( en )

2021-12-30

US11902413B2

true

US11902413B2 ( en )

2024-02-13

Family

ID=71097311

Family Applications (3)

Application Number

Title

Priority Date

Filing Date

US16/803,718

Active

2038-02-09

US11196541B2

( en )

2017-01-20

2020-02-27

Secure machine learning analytics using homomorphic encryption

US17/473,778

Active

2038-02-07

US11902413B2

( en )

2017-01-20

2021-09-13

Secure machine learning analytics using homomorphic encryption

US18/525,378

Pending

US20240113858A1

( en )

2017-01-20

2023-11-30

Systems and Methods for Performing Secure Machine Learning Analytics Using Homomorphic Encryption

Family Applications Before (1)

Application Number

Title

Priority Date

Filing Date

US16/803,718

Active

2038-02-09

US11196541B2

( en )

2017-01-20

2020-02-27

Secure machine learning analytics using homomorphic encryption

Family Applications After (1)

Application Number

Title

Priority Date

Filing Date

US18/525,378

Pending

US20240113858A1

( en )

2017-01-20

2023-11-30

Systems and Methods for Performing Secure Machine Learning Analytics Using Homomorphic Encryption

Country Status (1)

Country

Link

( 3 )

US11196541B2

( en )

Cited By (1)

* Cited by examiner, â Cited by third party

Publication number

Priority date

Publication date

Assignee

Title

US20250298908A1

( en )

2024-03-21

2025-09-25

Nvidia Corporation

Application programming interface to encrypt

Families Citing this family (37)

* Cited by examiner, â Cited by third party

Publication number

Priority date

Publication date

Assignee

Title

US10903976B2

( en )

2017-01-20

2021-01-26

Enveil, Inc.

End-to-end secure operations using a query matrix

US10972251B2

( en )

2017-01-20

2021-04-06

Enveil, Inc.

Secure web browsing via homomorphic encryption

US11507683B2

( en )

2017-01-20

2022-11-22

Enveil, Inc.

Query processing with adaptive risk decisioning

US11196541B2

( en )

2017-01-20

2021-12-07

Enveil, Inc.

Secure machine learning analytics using homomorphic encryption

US10873568B2

( en )

2017-01-20

2020-12-22

Enveil, Inc.

Secure analytics using homomorphic and injective format-preserving encryption and an encrypted analytics matrix

US11777729B2

( en )

2017-01-20

2023-10-03

Enveil, Inc.

Secure analytics using term generation and homomorphic encryption

US10706349B2

( en )

2017-05-25

2020-07-07

Texas Instruments Incorporated

Secure convolutional neural networks (CNN) accelerator

US12159216B1

( en )

2023-12-12

2024-12-03

Atombeam Technologies Inc

System and method for homomorphic compression

US11586743B2

( en )

2018-03-22

2023-02-21

Via Science, Inc.

Secure data processing

JP6917942B2

( en )

2018-04-11

2021-08-11

æ ªå¼ä¼ç¤¾æ¥ç«è£½ä½æ

Data analysis server, data analysis system, and data analysis method

JP7089303B2

( en )

2018-10-10

2022-06-22

æ ªå¼ä¼ç¤¾ã¢ã¯ã»ã«

Inference device, processing system, inference method and inference program

US10902133B2

( en )

2018-10-25

2021-01-26

Enveil, Inc.

Computational operations in enclave computing environments

US10817262B2

( en )

2018-11-08

2020-10-27

Enveil, Inc.

Reduced and pipelined hardware architecture for Montgomery Modular Multiplication

DE112020005424T5

( en )

2020-01-07

2022-09-01

Mitsubishi Electric Corporation

INFORMATION PROCESSING ESTABLISHMENT, INFORMATION PROCESSING PROCEDURE AND INFORMATION PROCESSING PROGRAM

EP3913884A1

( en )

2020-05-21

2021-11-24

Tata Consultancy Services Limited

Method and system for privacy preserving classification of websites url

CN111984960B

( en )

2020-07-13

2024-05-17

æ·±å³å¸æ·è®¯äºèç§ææéå¬å¸

Privacy protection equipment identification model design and use method based on homomorphic encryption

EP4203380A4

( en )

2020-08-21

2024-01-31

Almond Inc.

ENCRYPTION METHOD, TERMINAL EQUIPMENT, ENCRYPTION SYSTEM AND PROGRAM

CN113807530B

( en )

2020-09-24

2024-02-06

äº¬ä¸ç§ææ§è¡è¡ä»½æéå¬å¸

Information processing system, method and device

US11763043B2

( en )

2020-09-25

2023-09-19

Intel Corporation

Enabling late-binding of security features via configuration security controller for accelerator devices

US11601258B2

( en )

2020-10-08

2023-03-07

Enveil, Inc.

Selector derived encryption systems and methods

US11348035B2

( en )

2020-10-27

2022-05-31

Paypal, Inc.

Shared prediction engine for machine learning model deployment

US11902424B2

( en )

2020-11-20

2024-02-13

International Business Machines Corporation

Secure re-encryption of homomorphically encrypted data

US12131256B2

( en )

2021-01-06

2024-10-29

Hewlett Packard Enterprise Development Lp

System and method for training non-parametric machine learning model instances in a collaborative manner

US20220271914A1

( en )

2021-02-24

2022-08-25

Govermment of the United of America as represented by the Secretary of the Navy

System and Method for Providing a Secure, Collaborative, and Distributed Computing Environment as well as a Repository for Secure Data Storage and Sharing

US12388617B2

( en )

2021-03-25

2025-08-12

Nec Corporation

Private artificial neural networks with trusted execution environments and quadratic homomorphic encryption

US12001577B1

( en )

2021-09-30

2024-06-04

Amazon Technologies, Inc.

Encrypted machine learning models

CN113902443A

( en )

2021-10-20

2022-01-07

ä¸æµ·éµæ¹ç§ææéå¬å¸

Data processing method and device and server

US12362905B2

( en )

2021-12-09

2025-07-15

Electronics And Telecommunications Research Institute

Computing apparatus and method of integrating different homomorphic operations in homomorphic encryption

US20230185919A1

( en )

2021-12-15

2023-06-15

GM Global Technology Operations LLC

System and process using homomorphic encryption to secure neural network parameters for a motor vehicle

CN114398657B

( en )

2022-01-20

2025-09-16

æ¯ä»å®(æå·)ä¿¡æ¯ææ¯æéå¬å¸

Feature processing method for protecting privacy, feature prediction model training method and device

CN115442021A

( en )

2022-08-09

2022-12-06

ä¸å½é¶èè¡ä»½æéå¬å¸

Data matching method, device, system, equipment and medium

CN115378707B

( en )

2022-08-23

2024-03-29

è¥¿å®çµåç§æå¤§å¦

Self-adaptive sampling federal learning privacy protection method based on threshold homomorphism

TWI823592B

( en )

2022-09-30

2023-11-21

ä¸è¯é»ä¿¡è¡ä»½æéå¬å¸

System and method for performing encrypted mixing based on big number format and additive homomorphism

EP4679761A1

( en )

2024-07-12

2026-01-14

Orange

Privacy preserving neural network computation using partially homomorphic encryption

WO2026012834A1

( en )

2024-07-12

2026-01-15

Orange

Privacy preserving neural network computation using partially homomorphic encryption

CN120408705B

( en )

2025-04-22

2026-01-09

æ·±å³å¸å±çæ°ç§ä¿¡æ¯ææ¯æéå¬å¸

A Real-Time Data Classification and Hierarchical Encryption System and Method Based on Deep Learning

CN120834906B

( en )

2025-09-17

2026-02-03

æ±è¥¿è¦å¯å¦é¢

CKKS three-decision dynamic hierarchical encryption neural network training method and system

Citations (175)

* Cited by examiner, â Cited by third party

Publication number

Priority date

Publication date

Assignee

Title

US5732390A

( en )

1993-06-29

1998-03-24

Sony Corp

Speech signal transmitting and receiving apparatus with noise sensitive volume control

US6178435B1

( en )

1998-06-30

2001-01-23

International Business Machines Corporation

Method and system for performing a power of two estimation within a data processing system

US20020032712A1

( en )

1998-02-04

2002-03-14

Shuji Miyasaka

Exponential calculation device and decoding device

US20020073316A1

( en )

1998-02-03

2002-06-13

Thomas Collins

Cryptographic system enabling ownership of a secure process

US20020104002A1

( en )

2001-01-26

2002-08-01

Itaru Nishizawa

Database access method and system capable of concealing the contents of query

US20030037087A1

( en )

2001-08-14

2003-02-20

Sun Microsystems, Inc.

Apparatus and method for efficient modular exponentiation

US20030059041A1

( en )

2001-06-26

2003-03-27

Mackenzie Philip D.

Methods and apparatus for two-party generation of DSA signatures

US20030110388A1

( en )

1996-12-04

2003-06-12

Rainbow Technologies, Inc.

Software protection device and method

US6745220B1

( en )

2000-11-21

2004-06-01

Matsushita Electric Industrial Co., Ltd.

Efficient exponentiation method and apparatus

US6748412B2

( en )

2001-09-26

2004-06-08

Intel Corporation

Square-and-multiply exponent processor

US20040167952A1

( en )

2001-06-21

2004-08-26

Shay Gueron

Method and apparatus for carrying out efficiently arithmetic computations in hardware

US20050008152A1

( en )

2003-06-20

2005-01-13

Mackenzie Philip D.

Methods and apparatus for providing secure two-party public key cryptosystem

US20050076024A1

( en )

2003-10-06

2005-04-07

International Business Machines Corporation

System, method and program for database searching

US6910059B2

( en )

2002-07-09

2005-06-21

Silicon Integrated Systems Corp.

Apparatus and method for calculating an exponential calculating result of a floating-point number

US20050259817A1

( en )

2004-05-20

2005-11-24

Ramzan Zulfikar A

Method and apparatus for communication efficient private information retrieval and oblivious transfer

US20060008081A1

( en )

2004-07-09

2006-01-12

Nec Electronics Corporation

Modular-multiplication computing unit and information-processing unit

US20060008080A1

( en )

2004-07-09

2006-01-12

Nec Electronics Corporation

Modular-multiplication computing unit and information processing unit

US20070053507A1

( en )

2005-09-02

2007-03-08

Paris Smaragdis

Secure classifying of data with Gaussian distributions

US20070095909A1

( en )

2002-02-20

2007-05-03

David Chaum

Ballot integrity systems

US20070140479A1

( en )

2005-12-19

2007-06-21

Microsoft Corporation

Privacy-preserving data aggregation using homomorphic encryption

US20070143280A1

( en )

2005-12-19

2007-06-21

Microsoft Corporation

Determining cardinality of a parameter using hash values

US20090037504A1

( en )

2007-08-02

2009-02-05

Via Technologies, Inc.

Exponent Processing Systems and Methods

US20090083546A1

( en )

2004-10-19

2009-03-26

Palo Alto Research Center Incorporated

System And Method For Providing Private Inference Control

US20090193033A1

( en )

2005-05-19

2009-07-30

Zulfikar Amin Ramzan

Method and apparatus for communication efficient private information retrieval and oblivious transfer

US20090268908A1

( en )

2008-04-29

2009-10-29

Daniel Martin Bikel

Methods and Apparatus for Securely Classifying Data

US20090279694A1

( en )

2008-05-09

2009-11-12

Kenta Takahashi

Privacy-preserving scalar product calculation system, privacy-preserving scalar product calculation method and cryptographic key sharing system

US20090287837A1

( en )

2000-07-06

2009-11-19

David Paul Felsher

Information record infrastructure, system and method

US7712143B2

( en )

2006-09-27

2010-05-04

Blue Ridge Networks, Inc.

Trusted enclave for a computer system

US20100202606A1

( en )

2007-01-05

2010-08-12

Unoweb Inc.

Two strings private key (symmetric) encryption and decryption method

US20100205430A1

( en )

2009-02-06

2010-08-12

Shin-Yan Chiou

Network Reputation System And Its Controlling Method Thereof

US20100241595A1

( en )

2000-07-06

2010-09-23

David Paul Felsher

Information record infrastructure, system and method

US7849185B1

( en )

2006-01-10

2010-12-07

Raytheon Company

System and method for attacker attribution in a network security system

US7870398B2

( en )

2007-01-25

2011-01-11

International Business Machines Corporation

Integrity assurance of query result from database service provider

US20110026781A1

( en )

2009-07-02

2011-02-03

Carmel-Haifa University Economic Corporation Ltd.

System for secure face identification (scifi) and methods useful in conjunction therewith

US7937270B2

( en )

2007-01-16

2011-05-03

Mitsubishi Electric Research Laboratories, Inc.

System and method for recognizing speech securely using a secure multi-party computation protocol

US20110107105A1

( en )

2009-10-30

2011-05-05

International Business Machines Corporation

Message sending/receiving method

US20110110525A1

( en )

2009-11-10

2011-05-12

International Business Machines Corporation

Fully homomorphic encryption method based on a bootstrappable encryption scheme, computer program and apparatus

US20110243320A1

( en )

2010-03-30

2011-10-06

International Business Machines Corporation

Efficient Homomorphic Encryption Scheme For Bilinear Forms

US20110283099A1

( en )

2010-05-13

2011-11-17

Microsoft Corporation

Private Aggregation of Distributed Time-Series Data

US20120039469A1

( en )

2006-10-17

2012-02-16

Clay Von Mueller

System and method for variable length encryption

US20120054485A1

( en )

2010-08-25

2012-03-01

Sony Corporation

Terminal device, server, data processing system, data processing method, and program

US20120066510A1

( en )

2010-09-15

2012-03-15

At&T Intellectual Property I, L.P.

Methods, systems, and computer program products for performing homomorphic encryption and decryption on individual operations

US20120201378A1

( en )

2011-02-03

2012-08-09

Mohamed Nabeel

Efficient, remote, private tree-based classification using cryptographic techniques

US20120265794A1

( en )

2011-04-18

2012-10-18

Inside Secure

Montgomery multiplication circuit

US20120265797A1

( en )

2011-04-18

2012-10-18

Inside Secure

Montgomery multiplication method

US20130010950A1

( en )

2011-07-08

2013-01-10

Sap Ag

Public-Key Encrypted Bloom Filters With Applications To Private Set Intersection

US20130051551A1

( en )

2011-08-29

2013-02-28

Laila EL AIMANI

Signcryption method and device and corresponding signcryption verification method and device

US20130054665A1

( en )

2011-08-26

2013-02-28

Cognitive Electronics, Inc.

Methods and systems for performing exponentiation in a parallel processing environment

US20130114811A1

( en )

2011-11-08

2013-05-09

Petros T. Boufounos

Method for Privacy Preserving Hashing of Signals with Binary Embeddings

US20130148868A1

( en )

2009-09-04

2013-06-13

Gradiant

System for secure image recognition

US20130170640A1

( en )

2011-04-29

2013-07-04

International Business Machines Corporation

Fully Homomorphic Encryption

US20130191650A1

( en )

2012-01-25

2013-07-25

Massachusetts Institute Of Technology

Methods and apparatus for securing a database

US20130195267A1

( en )

2010-10-08

2013-08-01

Thomson Licensing

Public key encryption system based on the quadratic residuosity assumption

US20130198526A1

( en )

2006-02-22

2013-08-01

Fujitsu Semiconductor Limited

Secure processor

US8515058B1

( en )

2009-11-10

2013-08-20

The Board Of Trustees Of The Leland Stanford Junior University

Bootstrappable homomorphic encryption method, computer program and apparatus

US20130216044A1

( en )

2012-02-17

2013-08-22

International Business Machines Corporation

Homomorphic evaluation including key switching, modulus switching, and dynamic noise management

US20130230168A1

( en )

2010-11-15

2013-09-05

Nec Corporation

Information processing device, information processing method, and computer readable medium

US20130237242A1

( en )

2012-03-09

2013-09-12

Research In Motion Limited

Location identification of a portable electronic device based on characteristics of an operating environment of the portable electronic device

US20130246813A1

( en )

2011-11-11

2013-09-19

Nec Corporation

Database encryption system, method, and program

US8565435B2

( en )

2010-08-16

2013-10-22

International Business Machines Corporation

Efficient implementation of fully homomorphic encryption

US20130318351A1

( en )

2011-02-22

2013-11-28

Mitsubishi Electric Corporation

Similarity degree calculation system, similarity degree calculation apparatus, computer program, and similarity degree calculation method

US20130326224A1

( en )

2012-05-29

2013-12-05

Robert Bosch Gmbh

System and Method for Message Verification in Broadcast and Multicast Networks

US20130339722A1

( en )

2011-11-07

2013-12-19

Parallels IP Holdings GmbH

Method for protecting data used in cloud computing with homomorphic encryption

US20130339751A1

( en )

2012-06-15

2013-12-19

Wei Sun

Method for Querying Data in Privacy Preserving Manner Using Attributes

US20130346741A1

( en )

2012-06-21

2013-12-26

Korea Basic Science Institute

Method for authenticating low performance device

US20130346755A1

( en )

2012-06-21

2013-12-26

Microsoft Corporation

Homomorphic Signatures and Network Coding Signatures

KR101386294B1

( en )

2010-04-27

<td itemprop="pub

Secure machine learning analytics using homomorphic encryption — Enveil, Inc. (US11902413B2)

Related documents