From the 1 of 6 linked papers with an AI index.
6 papers
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…
SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing
Junmin Zhu, Siyu Liu, Jie Hu +7
The paper introduces SeedSmith, an LLM‑driven pipeline that automatically creates input seeds targeting specific sink functions and crash preconditions, improving the effectiveness…
Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery
Md Shafiuzzaman, Achintya Desai, Wenbo Guo +1
Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify asserti…
ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems
Zhuowen Yuan, Zhaorun Chen, Zhen Xiang +5
Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP serv…
SynthChain: A Synthetic Benchmark and Forensic Analysis of Advanced and Stealthy Software Supply Chain Attacks
Zhuoran Tan, Wenbo Guo, Taylor Brierley +3
Advanced software supply chain (SSC) attacks are increasingly runtime-only and leave fragmented evidence across hosts, services, and build/dependency layers, so any single telemetr…
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…