7 papers
Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks
Ying JinCheng, Minghui Xu, Yinhao Xiao +2
Large language models (LLMs) are safety-aligned before deployment to reduce harmful content generation. Yet neuron-level pruning attacks show that refusal can depend on a small set…
Semantic Validation of Packer Identification Tools: Characterization, Repair, and Downstream Impact
Fangtian Zhong, Zhuoyun Qian, Mengfei Ren +4
Packer identification tools are a critical foundation of malware analysis, directly affecting unpacking, behavioral analysis, malware classification, and threat attribution. Howeve…
When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs
Yue Li, Xiao Li, Hao Wu +4
Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration intr…
LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks
Ruoxi Wang, Kun Li, Minghui Xu +5
Dynamic Symbolic Execution (DSE) is a key technique in program analysis, widely used in software testing, vulnerability discovery, and formal verification. In distributed AI system…
We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems
Zhihao Li, Kun Li, Boyang Ma +3
The Model Context Protocol (MCP) has emerged as a widely adopted mechanism for connecting large language models to external tools and resources. While MCP promises seamless extensi…
Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask
Yue Li, Xiao Li, Hao Wu +5
Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a cri…