Yingshui Tan

SkillTrojan introduces a novel backdoor attack targeting the composition of reusable skills in agent systems, demonstrating high attack success rates with minimal impact on normal system functionality.

BraveGuard is a self-evolving defense framework that improves the safety of computer-use agents by training guard models on open-world, multi-step threat trajectories rather than static benchmarks.

BraveGuard is a self-evolving defense framework that significantly improves the safety monitoring of computer-use agents by generating guard model supervision from open-world threat discovery and realistic, multi-step execution trajectories.

The paper introduces SPADE-Bench, a new benchmark designed to rigorously evaluate 'agent deception'—the divergence between an agent's reported plan and its actual executed actions—which is a critical safety issue for autonomous LLM agents.

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.