SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
SPARD: 通过安全投影与相关性-多样性数据选择防御有害微调攻击
Shuhao Chen, Weisen Jiang, Yeqi Gong, Shengda Luo, Chengxiang Zhuo, Zang Li, James T. Kwok, Yu Zhang
机构
*
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(香港科学与技术大学计算机科学与工程系)
;
Department of Computer Science and Engineering, Southern University of Science and Technology(南方科技大学计算机科学与工程系)
;
Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程系)
;
Platform and Content Group, Tencent(腾讯平台与内容组)
;
Chinese Medicine Guangdong Laboratory(广东中医实验室)
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
DiffuGuard: 差分扩散语言模型中内在安全的丧失与恢复
Zherui Li, Zheng Nie, Zhenhong Zhou, Yue Liu, Yitong Zhang, Yu Cheng, Qingsong Wen, Kun Wang, Yufei Guo, Jiaheng Zhang
机构
*
Beijing University of Posts and Telecommunications(北京邮电大学)
;
National University of Singapore(新加坡国立大学)
;
Nanyang Technological University(南洋理工大学)
;
Tsinghua University(清华大学)
;
The Chinese University of Hong Kong(香港中文大学)
;
Squirrel Ai Learning(松鼠AI)
;
Peking University(北京大学)
机构
*
The Hong Kong University of Science and Technology(香港科学与技术大学)
;
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州))
;
New York University(纽约大学)
;
National University of Singapore(新加坡国立大学)
机构
*
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学)
;
Alibaba Group(阿里巴巴集团)
;
University of Chicago(芝加哥大学)
机构
*
The Conversational AI (CoAI) group, DCST, Tsinghua University(清华大学智能对话研究院)
;
National University of Singapore(新加坡国立大学)
;
Pattern Recognition Center, WeChat AI, Tencent Inc, China(腾讯人工智能研究院)
机构
*
School of Information Management, Wuhan University(武汉大学信息管理学院)
;
Nanyang Technological University(南洋理工大学)
;
Torr Vision Group, University of Oxford(牛津大学Torr视觉组)
Comments8 pages, 7 figures, 1 table. Work completed as part of the M.S. in Artificial Intelligence at the University of St. Thomas using publicly available models and datasets; all views and any errors are the author's own