Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation

1 May 2025

Papers citing "Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation"

3 / 3 papers shown

Title
Safe RLHF-V: Safe Reinforcement Learning from Human Feedback in Multimodal Large Language Models Yalan Qin Xiuying Chen Rui Pan Han Zhu C. Zhang ... Juntao Dai Chi-Min Chan Sirui Han Yike Guo Yiran Yang OffRL 82 4 0 22 Mar 2025
UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning Vaidehi Patil Elias Stengel-Eskin Joey Tianyi Zhou MU CLL 78 2 0 20 Feb 2025
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation Jaehong Yoon Shoubin Yu Vaidehi Patil Huaxiu Yao Joey Tianyi Zhou 79 16 0 16 Oct 2024