d.4.6

Documents about d.4.6

• Beyond Single-Vulnerability Evaluation: Closing the Engineering Decision Gap Between C Retrofits and Native Safety#616148arXiv (OAI Expanded)
• Beyond Single-Vulnerability Evaluation: Closing the Engineering Decision Gap Between C Retrofits and Native Safety#616648arXiv (All)
• Automating Static Code Analysis Through CI/CD Pipeline Integration#996946arXiv (All)
• Quipu: A Governed Bitemporal Knowledge Graph Store#623091arXiv (OAI Expanded)
• Quipu: A Governed Bitemporal Knowledge Graph Store#625364arXiv (All)
• A Secure, Manifest-Based Framework for Delegated Privilege Promotion#972440arXiv (All)
• Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents#822527arXiv (All)
• Bounded Agents: Delegation Security for Multi-Agent AI Systems#616517arXiv (OAI Expanded)
• Bounded Agents: Delegation Security for Multi-Agent AI Systems#617017arXiv (All)
• SoK: AI-Augmented Binary Reversing#971824arXiv (All)
• Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents#628166arXiv (OAI Expanded)
• Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents#630028arXiv (All)
• Federated Trust for Embodied Robot Capability Marketplaces#809856arXiv (OAI Expanded)
• Federated Trust for Embodied Robot Capability Marketplaces#819852arXiv (All)
• Agentic Settlement Protocol: An Application Profile for Refundable, Delayed-Fulfilment Agent Commerce on Stablecoin Rails#822601arXiv (All)
• Dr. Jekyll and Mr. Hyde: Two Faces of LLMs#182992arXiv
• Dr. Jekyll and Mr. Hyde: Two Faces of LLMs#183042arXiv Biology
• Dr. Jekyll and Mr. Hyde: Two Faces of LLMs#183092arXiv (OAI Expanded)
• Dr. Jekyll and Mr. Hyde: Two Faces of LLMs#183142arXiv (OAI)
• Structure/activity analysis of task-3 channel antagonists based on a 5,6,7,8 tetrahydropyrido[4,3-d]pyrimidine#948879Repositorio de Universidad Autónoma de Chile.
• Benchmarking Confidential Computing Performance on NVIDIA Blackwell GPUs#809474arXiv (OAI Expanded)
• Benchmarking Confidential Computing Performance on NVIDIA Blackwell GPUs#819470arXiv (All)
• ZK-Trace: Certified Collusion Tracing with Zero-Knowledge Credentials for Federated GNSS Interference Monitoring#986401arXiv (All)
• Numbat: Building and Verifying a Self-Contained Machine-Learning Stack#997632arXiv (All)
• Reachability, Not Observation: Containing Systems Whose Wiring Changes#1014308arXiv (All)
• Reproducible Evaluation of MoE Expert Caching: Replay Semantics, Workload Contamination, and Operating Regimes#668672arXiv (OAI Expanded)
• Reproducible Evaluation of MoE Expert Caching: Replay Semantics, Workload Contamination, and Operating Regimes#670737arXiv (All)
• Security Science (SecSci), Basic Concepts and Mathematical Foundations#972373arXiv (All)
• Analyzing Multi-Factor Authentication Through Cryptographic Security Properties#1013707arXiv (All)
• The Illusion of Local Privacy: Confidentiality Boundary Failures in Consumer LLM Serving Systems#1012707arXiv (All)
• Decoupling is a Necessity: Transformation-Agnostic Decompiled Code Recovery under Optimization and Obfuscation#779796arXiv (OAI Expanded)
• Decoupling is a Necessity: Transformation-Agnostic Decompiled Code Recovery under Optimization and Obfuscation#781171arXiv (All)
• The Native-Signature Boundary in Post-Quantum Distributed Authorization#926456arXiv (All)
• Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External Control#788503arXiv (OAI Expanded)
• Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External Control#792503arXiv (All)
• 22 U.S.C. § 262m-6 — Repealed. Pub. L. 101–240, title V, § 541(d)(4), Dec. 19, 1989, 103 Stat. 2518#580120US Code (LII)
• Towards Tackling Application Logic Flaws through Autonomous Formal-Logic Modeling and Automated Reasoning#997407arXiv (All)
• C~21~H~22~N~4~NiO~2~S~2~, 4.5(H~2~ O)#941509eCrystals
• Scan the Skill, Govern the Action: Composing Registry Verdicts with Runtime Consequence Control#999982arXiv (All)
• Context Is Not Authority: Structured Runtime Governance for Financial Market Agents#618752arXiv (OAI Expanded)
• Context Is Not Authority: Structured Runtime Governance for Financial Market Agents#620431arXiv (All)
• PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations#985320arXiv (All)
• Lipschitz-inspired HALRECT Algorithm for Derivative-free Global Optimization#986063arXiv (All)
• SoK: Advances and Open Problems in Web Tracking#1012025arXiv (All)
• CUSTOS: Toward Forensic-Ready Zero Trust at the Capture-Containment Boundary#820609arXiv (All)
• CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls#972205arXiv (All)
• Proof-of-Execution Memory: Defending LLM Agents Against Forged-Reasoning Attacks by Verifying What Actually Happened#617205arXiv (OAI Expanded)
• Proof-of-Execution Memory: Defending LLM Agents Against Forged-Reasoning Attacks by Verifying What Actually Happened#617705arXiv (All)
• 5,10-dioxo-N,N',1,2,6,7-hexaphenyl-5H,10H-dipyrrolo[1,2-a:1',2'-d]pyrazine-3,8-dicarboxamide dimethylsulfoxide solvate#930681eCrystals
• ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection#657063arXiv (OAI Expanded)