Yibo Li

The paper introduces WebAgentGuard, a novel reasoning-driven, multimodal guard model that effectively detects prompt injection attacks in vulnerable web agents without compromising their functionality.

This paper introduces TwoHamsters, a new benchmark that rigorously tests Multi-Concept Compositional Unsafety (MCCU) in text-to-image models, demonstrating that current state-of-the-art models and safety defenses are highly vulnerable to subtle, compositionally unsafe prompts.

The paper introduces Kumushi, a root-cause-driven patching agent that significantly improves automated vulnerability repair by focusing LLMs on the true source of bugs, outperforming existing methods and matching commercial agents.

The paper proposes WARD, a robust and efficient defense model that secures web agents against prompt injection attacks embedded in web content, achieving high recall and low false positives even against adaptive attacks.