Yao Liu

The paper proposes Federated Adversarial Unlearning (FAUN), a lightweight framework that uses adversarial optimization on a proxy dataset to rapidly and effectively remove the negative impact of poisoned client updates in federated learning.

This paper addresses the security vulnerability of OFDM-based Physical Layer Authentication (PLA) when channel fading exhibits correlation, proposing a new attack model and a measurable guideline to determine practical usability.

The paper introduces VIPER, a novel backdoor attack framework that exploits the functional fusion of malicious and benign logic within dynamic prompt architectures, demonstrating a new, high-risk threat.

The paper introduces a 'replication-first' paradigm for LLM behavioral benchmarking, demonstrating that this rigorous approach uncovers significant, non-obvious performance drops between successive model versions, such as a notable decline in advice-restraint for GPT-5.