发表机构
University of Illinois Urbana-Champaign; Stanford University; Georgia Institute of Technology; The University of Texas at Austin（伊利诺伊大学厄巴纳-香槟分校; 斯坦福大学; 佐治亚理工学院; 德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文首次统一综述了图像、视频和3D三种模态下扩散模型的对抗攻击与防御，提出了以任务为中心的分类体系，并分析了评估设置，指出了开放挑战和未来方向。
AI 中文摘要
扩散模型已成为视觉领域生成模型的主导家族。然而，其广泛的公开可用性使得大规模滥用成为可能，从而推动了关于对抗攻击与防御的研究迅速增长。据我们所知，本综述首次对图像、视频和3D这三种视觉模态的相关文献进行了统一回顾。我们引入了一个全面的、以任务为中心的分类体系：首先按模态划分文献；在每种模态内，将方法分为攻击和防御，然后根据它们所针对的生成任务进行分组，并在每个任务内按时间顺序呈现。此外，我们对其评估设置进行了深入分析，整合了用于评估的数据集、指标和基准。最后，我们指出了若干开放挑战，并概述了具体的未来研究方向。项目网页：此https URL
英文摘要
Diffusion models have become the dominant family of generative models in the visual domain. However, their widespread public availability enables misuse at scale, motivating a rapidly growing body of research on adversarial attacks and defenses. This survey provides, to our knowledge, the first unified review of this literature across three visual modalities: image, video, and 3D. We introduce a comprehensive, task-centric taxonomy: we first divide the literature by modality; within each modality, we separate methods into attacks and defenses, and then group them by the generative task they target, presenting them chronologically within each task. Moreover, we provide an in-depth analysis of their evaluation settings, consolidating the datasets, metrics, and benchmarks used to assess them. We conclude by identifying several open challenges and outlining concrete future research directions. Project Webpage: https://github.com/ozgurkara99/awesome-adv-attack-defense-on-diffusion
CommentsAccepted into Life-Cycle Intellectual Property Governance of Visual Generative Models Workshop at ECCV 2026
