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

Ozgur Kara, Tarik Can Ozden, Furkan Horoz, Zeqian Long, Haotian Xue +4 more
8/28/2026
cs.CVcs.CR
surveydiffusion-flow

Official code: ozgurkara99/awesome-adv-attack-defense-on-diffusion (10 stars, MIT, last commit 2026-10-20).

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

View on arXivView PDF

Code Implementations(1)

ozgurkara99/awesome-adv-attack-defense-on-diffusionOfficial100%
MIT
101Jun 30, 20264 days agoMIT

Similar Papers

A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication

87% match2024

IPG: Incremental Patch Generation for Generalized Adversarial Patch Training

85% match2025

Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models

85% match1 repo462024

Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey

85% match1 repo1032024

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models

85% match2026

TAIGen: Training-Free Adversarial Image Generation via Diffusion Models

85% match2025

Cite this paper

@article{kara2026survey,
  title  = {A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities},
  author = {Ozgur Kara and Tarik Can Ozden and Furkan Horoz and Zeqian Long and Haotian Xue and Yipu Chen and Oguzhan Akcin and Yongxin Chen and James Matthew Rehg},
  year   = {2026},
  eprint = {2609.05503},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.05503v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.05503.svg)](https://codeofpaper.com/paper/2609.05503)

Discussion