A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities

arXiv:2609.05503v1 Announce Type: new 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 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

Related

• IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack
• SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation
• Two Sides of the Same Coin: Co-Evolving Search for Cross-Task Attacks on Vision-Language Models
• TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger

Source: arXiv cs.CV | 2026-09-09