浏览条目

浏览/检索结果: 共7条,第1-7条 帮助

限定条件                
已选(0)清除 条数/页:   排序方式:
MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models 预印本
2024
作者:  Weng, Fenghua;  Xu, Yue;  Fu, Chengyan;  Wang, Wenjie
Adobe PDF(818Kb)  |  收藏  |  浏览/下载:89/0  |  提交时间:2024/09/02
Defending Jailbreak Attack in VLMs via Cross-modality Information Detector 预印本
2024
作者:  Xu, Yue;  Qi, Xiuyuan;  Qin, Zhan;  Wang, Wenjie
Adobe PDF(744Kb)  |  收藏  |  浏览/下载:82/0  |  提交时间:2024/08/26
Don't Say No: Jailbreaking LLM by Suppressing Refusal 预印本
2024
作者:  Zhou, Yukai;  Wang, Wenjie
Adobe PDF(2592Kb)  |  收藏  |  浏览/下载:130/0  |  提交时间:2024/05/15
LinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models 预印本
2024
作者:  Xu, Yue;  Wang, Wenjie
Adobe PDF(893Kb)  |  收藏  |  浏览/下载:125/1  |  提交时间:2024/05/15
IGAMT: Privacy-Preserving Electronic Health Record Synthesization with Heterogeneity and Irregularity 会议论文
2024 ASSOCIATION FOR THE ADVANCEMENT OF ARTIFICIAL INTELLIGENCE, Vancouver, BC, Canada, February 20, 2024 - February 27, 2024
作者:  Wang WJ(王雯婕);  Pengfei Tang;  Jian Lou;  Yuanming Shao;  Lance Waller
Adobe PDF(2822Kb)  |  收藏  |  浏览/下载:187/0  |  提交时间:2024/03/21
LinkPrompt: Natural and Universal Adversarial Attacks on Prompt-based Language Models 会议论文
2024 ANNUAL CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, Hybrid, Mexico City, Mexico, June 16, 2024 - June 21, 2024
作者:  Xu Y(徐悦);  Wang WJ(王雯婕)
Adobe PDF(893Kb)  |  收藏  |  浏览/下载:192/2  |  提交时间:2024/03/21
Demo: Certified Robustness on Toolformer 会议论文
ASSOCIATION FOR COMPUTING MACHINERY, Copenhagen, Denmark, November 26, 2023 - November 30, 2023
作者:  Xu, Yue;  Wang, Wenjie
Adobe PDF(746Kb)  |  收藏  |  浏览/下载:206/1  |  提交时间:2023/11/21