MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

ArXi:2602.23798v2 Announce Type: replace Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose MPU, an algorithm-agnostic privacy-preserving Multiple Perturbed Copies Unlearning framework that primarily