🛡️ Vulnerability Research - amy.throwaway.lovely · Scour

VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database 🛡️Exploit Mitigations

arxiv.org·1d

Vulnerability Abundance: A formal proof of infinite vulnerabilities in code 🛡️Exploit Mitigations

arxiv.org·11h

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents 🛡️Exploit Mitigations

arxiv.org·4d

Program Analysis Guided LLM Agent for Proof-of-Concept Generation ✅Formal Verification

arxiv.org·11h

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery 🧮Symbolic Execution

arxiv.org·1d

Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study 🎯Taint Analysis

arxiv.org·4d

An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations 🛡️Exploit Mitigations

arxiv.org·11h

Policy-Driven Vulnerability Risk Quantification framework for Large-Scale Cloud Infrastructure Data Security 🐧Kernel Exploitation

arxiv.org·1d

IPEK: Intelligent Priority-Aware Event-Based Trust with Asymmetric Knowledge for Resilient Vehicular Ad-Hoc Networks 🌐Protocol Fuzzing

arxiv.org·11h

A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection 🛡️Exploit Mitigations

arxiv.org·2d

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models 💾Binary Analysis

arxiv.org·4d

TADP-RME: A Trust-Adaptive Differential Privacy Framework for Enhancing Reliability of Data-Driven Systems 🎯Taint Analysis

arxiv.org·11h

Towards Predicting Multi-Vulnerability Attack Chains in Software Supply Chains from Software Bill of Materials Graphs 💾Binary Analysis

arxiv.org·2d

PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy 🛡️Exploit Mitigations

arxiv.org·1d

"Because we are no longer ashamed of our disabilities, we are proud": Advocating and Reclaiming Next-Gen Accessibility Symbols 🧩Intermediate Representation

arxiv.org·11h

AI Disclosure with DAISY 🔣Type Systems

arxiv.org·4d

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training 🧩Intermediate Representation

arxiv.org·11h

Broken Quantum: A Systematic Formal Verification Study of Security Vulnerabilities Across the Open-Source Quantum Computing Simulator Ecosystem 🔌Hardware Security

arxiv.org·1d

Optimization of 32-bit Unsigned Division by Constants on 64-bit Targets 💾Binary Analysis

arxiv.org·11h

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement 🛡️Exploit Mitigations

arxiv.org·2d

Loading more...