 CLEAR: Character Unlearning in Textual and Visual ModalitiesAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video GenerationInternational Conference on Learning Representations (ICLR), 2024 |
 Multimodal Pragmatic Jailbreak on Text-to-image ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Mission Impossible: A Statistical Perspective on Jailbreaking LLMsNeural Information Processing Systems (NeurIPS), 2024 |
 The Emerged Security and Privacy of LLM Agent: A Survey with Case StudiesACM Computing Surveys (ACM CSUR), 2024 |
 |
 What matters when building vision-language models?Neural Information Processing Systems (NeurIPS), 2024 |
 Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language ModelsEuropean Conference on Computer Vision (ECCV), 2024 |
