ReasoningBomb

AI & ML interests

None defined yet.

Recent Activity

Xiaogeng-SheltonLiu  authored a paper about 2 months ago

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Xiaogeng-SheltonLiu  authored a paper about 2 months ago

Doxing via the Lens: Revealing Privacy Leakage in Image Geolocation for Agentic Multi-Modal Large Reasoning Model

Xiaogeng-SheltonLiu  authored a paper about 2 months ago

Code Agent can be an End-to-end System Hacker: Benchmarking Real-world Threats of Computer-use Agent

View all activity

Team members 1