Wanlei Zhou

This paper systematically revisits and expands the threat model for backdoor attacks on semantic segmentation, proposing a unified framework (BADSEG) that demonstrates severe, previously overlooked vulnerabilities in current and emerging segmentation models.

The paper proposes a comprehensive framework for LLM-based agent unlearning, enabling agents to selectively forget specific knowledge (states, trajectories, or environments) while maintaining performance and resisting knowledge inference by adversaries.

The paper proposes Two-stage Backdoor Hijacking (TSBH) to create persistent, trigger-activated malicious behaviors by manipulating the observable Chain-of-Thought (CoT) process in Large Language Models.

The paper proposes Cluster Segregation Concealment (CSC), a novel defense that identifies and neutralizes backdoor triggers by relabeling poisoned samples to a virtual class, achieving near-zero attack success rates with minimal accuracy loss.

The paper introduces CAESAR, a novel multi-agent framework that coordinates LLM agents across five specialized roles to improve success rates and stability in complex, multi-stage cyber intrusion tasks.