Liang Chen

CoopGuard is a novel stateful, multi-round defense framework using cooperative agents to significantly reduce the success rate of evolving adversarial attacks against Large Language Models.

AITH is a novel post-quantum continuous delegation protocol designed to securely establish, manage, and revoke trust relationships between humans and autonomous AI agents operating in variable environments.

The paper introduces EditRisk-Bench, a novel benchmark designed to systematically evaluate the safety risks and downstream reasoning corruption caused by malicious knowledge editing in large language models.

The paper proposes FeasiGen, a method to automatically create infeasible tasks for tool-using agents, and finds that most current agents struggle significantly to detect and stop when faced with such impossible tasks.

The paper introduces Crafter, a multi-agent harness that significantly improves the generation of editable, publication-quality scientific figures from diverse inputs, addressing the limitations of existing single-purpose systems.

This paper proposes a unified framework for inference-time augmentation to improve the robustness of physiological signal classification in real-world deployments.