4 papers
When Context Gets Root: Privilege Escalation in LLM Harnesses
Xingbang He, Yuanwei Chen, Yi Qian +6
Instruction hierarchy is a model-side defense that assigns instructions different levels of privilege according to their sources. These levels constrain which content may direct mo…
Discovering 100+ Compiler Defects in 72 Hours via LLM-Driven Semantic Logic Recomposition
Xingbang He, Yuanwei Chen, Hao Wu +9
Compilers constitute the foundational root-of-trust in software supply chains; however, their immense complexity inevitably conceals critical defects. Recent research has attempted…
Mind the Gap: Action Rebinding Attacks against Android GUI Agents
Yi Qian, Kunwei Qian, Xingbang He +7
Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content and inject inputs across application bo…
Unleashing the Power of LLM to Infer State Machine from the Protocol Implementation
Haiyang Wei, Ligeng Chen, Zhengjie Du +7
State machines are essential for enhancing protocol analysis to identify vulnerabilities. However, inferring state machines from network protocol implementations is challenging due…