3 papers
cs.CR2026
Mind the Gap: Action Rebinding Attacks against Android GUI Agents
Yi Qian, Kunwei Qian, Xingbang He +7
The paper reveals a new cross-application attack called Action Rebinding that lets a harmless Android app hijack the actions of high‑privilege GUI agents, enabling privileged opera…
cs.SE2026
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…
cs.CR2025
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…