返回全部动态
跨模态扩散模型对抗攻击与防御综述
原标题：A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities
AI 摘要
这篇综述首次统一回顾了扩散模型在图像、视频和3D三种视觉模态下的对抗攻击与防御研究。文章提出了一种以任务为中心的全面分类法，按模态、攻击/防御和生成任务组织文献，并深入分析了评估设置，包括数据集、指标和基准。最后，作者指出了若干开放挑战并提出了具体的未来研究方向。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities Abstract 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
发布时间：2026-09-09 12:00
抓取时间：2026-09-09 12:27
来源机构：arXiv