Jianliang Xu

Decoupling the Class Label and the Target Concept in Machine Unlearning

SeedThink: Test-Time Control via Seed-Thought Initialization

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts

Decoupling the Class Label and the Target Concept in Machine Unlearning

Alignment-Aware Model Extraction Attacks on Large Language Models