cs.AI updates on arXiv.org 20小时前
When and Where do Data Poisons Attack Textual Inversion?
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文系统分析了扩散模型中文本反转技术的毒攻击问题,提出了一种名为Safe-Zone Training的防御机制,通过JPEG压缩、限制训练时间步长和损失掩码等方法,显著提高了文本反转的鲁棒性。

arXiv:2507.10578v1 Announce Type: cross Abstract: Poisoning attacks pose significant challenges to the robustness of diffusion models (DMs). In this paper, we systematically analyze when and where poisoning attacks textual inversion (TI), a widely used personalization technique for DMs. We first introduce Semantic Sensitivity Maps, a novel method for visualizing the influence of poisoning on text embeddings. Second, we identify and experimentally verify that DMs exhibit non-uniform learning behavior across timesteps, focusing on lower-noise samples. Poisoning attacks inherit this bias and inject adversarial signals predominantly at lower timesteps. Lastly, we observe that adversarial signals distract learning away from relevant concept regions within training data, corrupting the TI process. Based on these insights, we propose Safe-Zone Training (SZT), a novel defense mechanism comprised of 3 key components: (1) JPEG compression to weaken high-frequency poison signals, (2) restriction to high timesteps during TI training to avoid adversarial signals at lower timesteps, and (3) loss masking to constrain learning to relevant regions. Extensive experiments across multiple poisoning methods demonstrate that SZT greatly enhances the robustness of TI against all poisoning attacks, improving generative quality beyond prior published defenses. Code: www.github.com/JStyborski/Diff_Lab Data: www.github.com/JStyborski/NC10

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

扩散模型 毒攻击 文本反转 防御机制 Safe-Zone Training
相关文章