11 papers
Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents
Kaixin Wang, Tianlin Li, Xiaoyu Zhang +7
Code large language models (CodeLLMs) and agents are increasingly being integrated into complex software engineering tasks spanning the entire Software Development Life Cycle (SDLC…
Evaluating Large Language Models for Line-Level Vulnerability Localization
Jian Zhang, Chong Wang, Anran Li +4
Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulne…
A Vision for Auto Research with LLM Agents
Chengwei Liu, Chong Wang, Jiayue Cao +16
This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Levera…
VFArchÄ: A Dual-Mode Framework for Locating Vulnerable Functions in Open-Source Software
Lyuye Zhang, Jian Zhang, Kaixuan Li +6
Software Composition Analysis (SCA) has become pivotal in addressing vulnerabilities inherent in software project dependencies. In particular, reachability analysis is increasingly…
Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization
Yihao Huang, Chong Wang, Xiaojun Jia +5
Universal goal hijacking is a kind of prompt injection attack that forces LLMs to return a target malicious response for arbitrary normal user prompts. The previous methods achieve…
Fixing Outside the Box: Uncovering Tactics for Open-Source Security Issue Management
Lyuye Zhang, Jiahui Wu, Chengwei Liu +5
In the rapidly evolving landscape of software development, addressing security vulnerabilities in open-source software (OSS) has become critically important. However, existing rese…