VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models
VOID: 击败潜在扩散模型中的未授权模仿
机构 * School of Cyber Science and Engineering, Wuhan University(武汉大学网络空间安全学院) ; School of Computer Science, Wuhan University(武汉大学计算机学院) ; Institute for Math&AI, Wuhan University(武汉大学数学与人工智能研究所) ; The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) ; School of Cyber Science and Engineering, Xi’an Jiaotong University(西安交通大学网络空间安全学院)
AI总结 针对潜在扩散模型被用于未授权模仿的问题,提出VOID防御框架,通过操纵模型内在随机性,放大潜在编码误差并抵消目标引导信号,实现语义破坏,阻止未授权模仿,同时将扰动限制在人眼不可感知区域。
Comments Extended full version with more comprehensive experimental results. To appear in the 35th USENIX Security Symposium (USENIX Security 2026)