Qinghua Mao

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.

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 FRA-Attack, a frequency-domain regularization method, to significantly improve the transferability of adversarial attacks against closed-source Multimodal Large Language Models (MLLMs).

This paper introduces GraphSteal, an attack framework demonstrating that Graph RAG systems can leak substantial portions of a hidden knowledge graph by treating them as structural oracles.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.