4 papers · 1 filter
From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers
Suyue Guo, Stijn Pletinckx, Tianle Yu +5
Existing fuzzers for PDF readers rely on simple test cases that involve only individual API calls, leading to limited coverage and potentially missing vulnerabilities that require…
Multi-Agent Taint Specification Extraction for Vulnerability Detection
Jonah Ghebremichael, Saastha Vasan, Saad Ullah +6
Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results compared to traditional pattern-…
From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
Saad Ullah, Praneeth Balasubramanian, Wenbo Guo +5
High-quality datasets of real-world vulnerabilities and their corresponding verifiable exploits are crucial resources in software security research. Yet such resources remain scarc…
LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks
Saad Ullah, Mingji Han, Saurabh Pujar +3
Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking.…