arxiv:2602.00154
Liu
Xiaogeng-SheltonLiu
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection
Guardrail Models authored a paper about 1 month ago
Doxing via the Lens: Revealing Privacy Leakage in Image Geolocation for
Agentic Multi-Modal Large Reasoning Model authored a paper about 1 month ago
Code Agent can be an End-to-end System Hacker: Benchmarking Real-world
Threats of Computer-use AgentOrganizations
models 0
None public yet
datasets 0
None public yet