3 papers
cs.CR2026
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…
cs.CR2026
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…
cs.CY2025
The Liabilities of Robots.txt
Chien-yi Chang, Xin He
This paper explores the legal implications of violating "robots.txt", a technical standard widely used by webmasters to communicate restrictions on automated access to website cont…