arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.01369cs.LGcs.CRcs.CV
收藏

扩散模型的多模态脆弱性研究

On the Multi-modal Vulnerability of Diffusion Models

Tsinghua University(清华大学);Nanyang Technological University(南洋理工大学);Sun Yat-sen University(中山大学)

Dingcheng Yang, Yang Bai, Xiaojun Jia, Yang Liu, Xiaochun Cao, Wenjian Yu

AI总结:

本文首次可视化扩散模型的文本与图像特征空间差异,提出利用多模态先验的MMP-Attack方法,通过附加后缀操纵生成结果,在消除原对象的同时生成目标对象,操纵能力与效率优于现有研究。

摘要:

扩散模型已被广泛应用于各类图像生成任务,展现出图像与文本模态之间的非凡关联。尽管已有研究分别从文本和图像模态的角度探讨了扩散模型的脆弱性,但当前的研究格局尚未深入考察由多模态整合所引发的脆弱性,特别是通过文本与视觉特征的联合分析所暴露的问题。在本文中,我们首次对扩散模型嵌入的文本与图像特征空间进行可视化,并观察到显著差异:提示在文本特征空间中呈现混沌分布,而在图像特征空间中则根据其主题聚集。这些有趣的发现可能揭示了扩散模型内部两种模态在鲁棒性上的潜在错位。基于这一观察,我们提出了MMP-Attack,该方法利用多模态先验(MMP),通过在原始提示后附加特定后缀来操纵扩散模型的生成结果。具体而言,我们的目标是诱导扩散模型生成特定对象,同时消除原始对象。我们的MMP-Attack在操纵能力和效率上均优于现有研究,展现出显著优势。我们的代码已在\url{https://github.com/ydc123/MMP-Attack}公开。

英文摘要:

Diffusion models have been widely deployed in various image generation tasks, demonstrating an extraordinary connection between image and text modalities. Although prior studies have explored the vulnerability of diffusion models from the perspectives of text and image modalities separately, the current research landscape has not yet thoroughly investigated the vulnerabilities that arise from the integration of multiple modalities, specifically through the joint analysis of textual and visual features. In this paper, we are the first to visualize both text and image feature space embedded by diffusion models and observe a significant difference. The prompts are embedded chaotically in the text feature space, while in the image feature space they are clustered according to their subjects. These fascinating findings may underscore a potential misalignment in robustness between the two modalities that exists within diffusion models. Based on this observation, we propose MMP-Attack, which leverages multi-modal priors (MMP) to manipulate the generation results of diffusion models by appending a specific suffix to the original prompt. Specifically, our goal is to induce diffusion models to generate a specific object while simultaneously eliminating the original object. Our MMP-Attack shows a notable advantage over existing studies with superior manipulation capability and efficiency. Our code is publicly available at \url{https://github.com/ydc123/MMP-Attack}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑