💾 Binary Analysis - amy.throwaway.lovely · Scour

Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation ✅Formal Verification

arxiv.org·5h

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

arxiv.org·1d

TypePro: Boosting LLM-Based Type Inference via Inter-Procedural Slicing 🔣Type Systems

arxiv.org·4d

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

arxiv.org·5h

Typify: A Lightweight Usage-driven Static Analyzer for Precise Python Type Inference 🔣Type Systems

arxiv.org·2d

LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering 🔄Reverse Engineering

arxiv.org·2d

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

arxiv.org·4d

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

arxiv.org·1d

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

arxiv.org·2d

Test-Oriented Programming: rethinking coding for the GenAI era 🔀Concolic Execution

arxiv.org·5h

Vulnerability Detection with Interprocedural Context in Multiple Languages: Assessing Effectiveness and Cost of Modern LLMs 🛡️Exploit Mitigations

arxiv.org·5h

Combining Static Code Analysis and Large Language Models Improves Correctness and Performance of Algorithm Recognition ⚡JIT Exploitation

arxiv.org·4d

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation ⚡JIT Exploitation

arxiv.org·5h

Log-based, Business-aware REST API Testing 📟Firmware Analysis

arxiv.org·5h

What Are Adversaries Doing? Automating Tactics, Techniques, and Procedures Extraction: A Systematic Review 🚩CTF

arxiv.org·4d

Accurate Residues for Floating-Point Debugging ⚡JIT Exploitation

arxiv.org·1d

ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision? 🔀Concolic Execution

arxiv.org·5h

SALLIE: Safeguarding Against Latent Language & Image Exploits 🛡️Exploit Mitigations

arxiv.org·1d

Cross-Tokenizer LLM Distillation through a Byte-Level Interface 🧩Intermediate Representation

arxiv.org·5h

NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure 🧩Intermediate Representation

arxiv.org·3d

Loading more...