Language Guided Adversarial Purification

[2309.10348] Language Guided Adversarial Purification Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2309.10348 (cs) [Submitted on 19 Sep 2023] Title: Language Guided Adversarial Purification Authors: Himanshu Singh , A V Subramanyam View a PDF of the paper titled Language Guided Adversarial Purification, by Himanshu Singh and 1 other authors View PDF HTML (experimental) Abstract: Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but often computationally intensive. Recent strides in diffusion and score networks have improved image generation and, by extension, adversarial purification. Another highly efficient class of adversarial defense methods known as adversarial training requires specific knowledge of attack vectors, forcing them to be trained extensively on adversarial examples. To overcome these limitations, we introduce a new framework, namely Language Guided Adversarial Purification (LGAP), utilizing pre-trained diffusion models and caption generators to defend against adversarial attacks. Given an input image, our method first generates a caption, which is then used to guide the adversarial purification process through a diffusion network. Our approach has been evaluated against strong adversarial attacks, proving its effectiveness in enhancing adversarial robustness. Our results indicate that LGAP outperforms most existing adversarial defense techniques without requiring specialized network training. This underscores the generalizability of models trained on large datasets, highlighting a promising direction for further research. Subjects: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV) MSC classes: 68T45 (Primary), 68T10 (Secondary) ACM classes: I.5.4 Cite as: arXiv:2309.10348 [cs.LG] (or arXiv:2309.10348v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2309.10348 Focus to learn more arXiv-issued DOI via DataCite Journal reference: 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7685-7689 Related DOI : https://doi.org/10.1109/ICASSP48485.2024.10446676 Focus to learn more DOI(s) linking to related resources Submission history From: Himanshu Singh [ view email ] [v1] Tue, 19 Sep 2023 06:17:18 UTC (1,752 KB) Full-text links: Access Paper: View a PDF of the paper titled Language Guided Adversarial Purification, by Himanshu Singh and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2023-09 Change to browse by: cs cs.CR cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• AMRM-Pure: Semantic-Preserving Adversarial Purification#343384
• Information Theoretic Adversarial Training of Large Language Models#160754
• Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation#1154971
• Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance#280138
• PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models#303213