Paper-Conference

Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models

DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment

PROFL: A Privacy-Preserving Federated Learning Method with Stringent Defense Against Poisoning Attacks