Zhiyuan Yu

The paper proposes MMGuard, a proactive defense mechanism that injects unlearnable, human-imperceptible perturbations into multimodal data to prevent unauthorized fine-tuning of Large Vision-Language Models (LVLMs).

PrivScope is a novel on-device governor that enforces task-scoped disclosure, ensuring sensitive information is abstracted to the least revealing form before being sent to a cloud language model, significantly reducing data leakage without compromising task utility.