5 papers
FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
Naen Xu, Jinghuai Zhang, Ping He +6
Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible t…
HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
Jingxiao Yang, Ping He, Tianyu Du +2
Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable to adversarial attacks that ex…
Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinement
Xiaonan Luo, Yue Huang, Ping He +1
High-quality Question-Answer (QA) datasets are foundational for reliable Large Language Model (LLM) evaluation, yet even expert-crafted datasets exhibit persistent gaps in domain c…
Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
Ping He, Changjiang Li, Binbin Zhao +2
The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agen…
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
Boyu Zhang, Ping He, Tianyu Du +4
With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current waterm…