Haibo Hu

The paper introduces Argus, a novel multi-agent framework that reorchestrates Static Application Security Testing (SAST) by integrating LLMs with existing tools to achieve superior, reliable, and cost-effective vulnerability detection.

The paper identifies 'unintended long-term state poisoning'—a security risk where routine user interactions gradually corrupt an LLM agent's persistent state—and proposes a defense mechanism called StateGuard.

The paper proposes a novel cross-modal backdoor attack that exploits the vulnerability of lightweight connectors in multimodal LLMs, demonstrating high attack success rates across different modalities.

This paper introduces Mobius Injection, a novel, lightweight attack that weaponizes autonomous LLM agents into zombie nodes to launch highly scalable AbO-DDoS attacks by exploiting a vulnerability called Semantic Closure.