Zihan Zhou

Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak Strategies

Stealthy Jailbreaking Attacks via Hyperbolic Hamiltonian Dynamics and Möbius Fusion

On Training Mixture-of-Experts: A Social Choice Perspective

Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning

Riemannian Low-Rank Adaptation for Federated Fine-Tuning of Foundation Models