6 papers
SEASONED: Semantic-Enhanced Self-Counterfactual Explainable Detection of Adversarial Exploiter Contracts
Xng Ai, Shudan Lin, Zecheng Li +3
Decentralized Finance (DeFi) attacks have resulted in significant losses, often orchestrated through Adversarial Exploiter Contracts (AECs) that exploit vulnerabilities in victim s…
SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents
Jianming Chang, Jieke Shi, Yunbo Lyu +5
Static program slicing, which extracts the executable portions of a program that affect the values at a specific location, supports many software analysis tasks such as debugging a…
Rethinking LLM-Based RTL Code Optimization Via Timing Logic Metamorphosis
Zhihao Xu, Bixin Li, Lulu Wang
Register Transfer Level(RTL) code optimization is crucial for achieving high performance and low power consumption in digital circuit design. However, traditional optimization meth…
Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models
Jianming Chang, Xin Zhou, Lulu Wang +2
Automated issue fixing is a critical task in software debugging and has recently garnered significant attention from academia and industry. However, existing fixing techniques pred…
Learning Graph-based Patch Representations for Identifying and Assessing Silent Vulnerability Fixes
Mei Han, Lulu Wang, Jianming Chang +2
Software projects are dependent on many third-party libraries, therefore high-risk vulnerabilities can propagate through the dependency chain to downstream projects. Owing to the s…
On Code Reuse from StackOverflow: An Exploratory Study on Jupyter Notebook
Mingke Yang, Yuming Zhou, Bixin Li +1
Jupyter Notebook is a popular tool among data analysts and scientists for working with data. It provides a way to combine code, documentation, and visualizations in a single, inter…