首份跨模态扩散模型攻防综述，覆盖图像、视频与3D生成。
A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities
- 按模态与生成任务分类，系统梳理攻击与防御方法。
- 整合主流数据集、评估指标与基准测试，统一评价体系。
- 适合关注生成模型安全的科研人员与工程师参考。
扩散模型已成为视觉领域主导的生成模型家族。然而，其广泛公开可用性导致大规模滥用风险，推动了对抗攻击与防御研究的迅速发展。本综述首次系统性地对图像、视频和3D三个视觉模态的对抗攻防文献进行了统一回顾。我们提出一个以任务为中心的全面分类体系：首先按模态划分，每类中再分攻击与防御方法，并按目标生成任务分组，按时间顺序呈现。此外，我们深入分析了各类方法的评估设置，整合了所用数据集、评估指标与基准测试。最后，我们识别出若干开放挑战，并提出了具体的研究方向。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。