5 papers
Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents
Ratnadira Widyasari, Martin Weyssow, Ivana Clairine Irsan +6
Detecting vulnerabilities in source code remains a critical yet challenging task, especially when benign and vulnerable functions share significant similarities. In this work, we i…
Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection
Ting Zhang, Chengran Yang, Yindu Su +8
Recent advancements in generative AI have led to the widespread adoption of large language models (LLMs) in software engineering, addressing numerous long-standing challenges. Howe…
Towards Reliable LLM-Driven Fuzz Testing: Vision and Road Ahead
Yiran Cheng, Hong Jin Kang, Lwin Khin Shar +4
Fuzz testing is a crucial component of software security assessment, yet its effectiveness heavily relies on valid fuzz drivers and diverse seed inputs. Recent advancements in Larg…
Grey-Box Fuzzing in Constrained Ultra-Large Systems: Lessons for SE Community
Jiazhao Yu, Yanlun Tu, Zhanlei Zhang +5
Testing ultra-large microservices-based FinTech systems presents significant challenges, including restricted access to production environments, complex dependencies, and stringent…
CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics
Yikun Li, Ting Zhang, Ratnadira Widyasari +13
Accurate identification of software vulnerabilities is crucial for system integrity. Vulnerability datasets, often derived from the National Vulnerability Database (NVD) or directl…