From the 1 of 4 linked papers with an AI index.
4 papers
Agentic Vulnerability Reasoning on COTS Binaries
Hwiwon Lee, Jongseong Kim, Lingming Zhang
The paper introduces SLYP, a REACT-style pipeline that enables large language model agents to discover and validate vulnerabilities directly in commercial off‑the‑shelf (COTS) Wind…
Weaver: Fuzzing JavaScript Engines at the JavaScript-WebAssembly Boundary
Lingming Zhang, Binbin Zhao, Puzhuo Liu +4
The security of modern JavaScript (JS) engines is critical since they provide the primary defense mechanism for executing untrusted code on the web. The recent integration of WebAs…
A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications
Boyang Yang, Zijian Cai, Fengling Liu +5
Large language models (LLMs) are reshaping automated program repair. We present a unified taxonomy that groups 62 recent LLM-based repair systems into four paradigms defined by par…
SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
Hwiwon Lee, Ziqi Zhang, Hanxiao Lu +1
Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycl…