Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddings
Zero2Text: 无训练跨域反向攻击文本嵌入
Doohyun Kim, Donghwa Kang, Kyungjae Lee, Hyeongboo Baek, Brent Byunghoon Kang
机构
*
School of Computing, Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院计算学院)
;
Graduate School of Information Security, Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院信息安全研究生院)
;
Department of Artificial Intelligence, University of Seoul, Seoul, Republic of Korea(首尔大学人工智能系)
;
Department of Computer Science, University of Seoul, Seoul, Republic of Korea(首尔大学计算机科学系)
CommentsMajor revision accepted in Computational Economics, December 31, 2025. This version incorporates extensive revisions based on the reviewers' comments, with substantial changes
机构
*
The University of Hong Kong(香港大学)
;
University of Wisconsin-Madison(威斯康星大学麦迪逊分校)
;
The Simons Institute for the Theory of Computing at the University of California, Berkeley(伯克利大学计算理论研究所)
Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI
从神经科学中汲取教训:如何通过整合动作、组合结构和事件记忆来实现安全、可解释和类人的人工智能
Rajesh P. N. Rao, Vishwas Sathish, Linxing Preston Jiang, Matthew Bryan, Prashant Rangarajan
The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents
沉默学者问题:一种基于概率的框架,用于在LLM代理中打破知识不对称性
Zan-Kai Chong, Hiroyuki Ohsaki, Bryan Ng
机构
*
School of Science and Technology(科学与技术学院)
;
Kwansei Gakuin University(冈山大学)
;
School of Engineering & Computer Science(工程与计算机科学学院)
;
Victoria University of Wellington(惠灵顿维多利亚大学)