mlsanityData to 7 Oct 2026

DiffDefense: Defending against Adversarial Attacks via Diffusion Models

arXiv 2309.03702 ↗First posted 7 Sep 2023cs.LG cs.CR cs.CVcited by 2

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves. The susceptibility of machine learning models to minor input perturbations renders them vulnerable to adversarial attacks. While diffusion-based methods are typically disregarded for adversarial defense due to their slow reverse process, this paper demonstrates that our proposed method offers robustness against adversarial threats while preserving clean accuracy, speed, and plug-and-play compatibility. Code at: https://github.com/HondamunigePrasannaSilva/DiffDefence.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 33 of its 37 references that are in the map. First posted on arXiv 7 Sep 2023.

Builds on

33 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Guided Diffusion Model for Adversarial Purification from Random Noise22 Jun
  2. 2022Guided Diffusion Model for Adversarial Purification30 May
  3. 2022Diffusion Models for Adversarial Purification16 May
  4. 2021Adversarial purification with Score-based generative models11 Jun

Other references · 29

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2019An Introduction to Variational Autoencoderscited by 997
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  10. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  11. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  12. 2017One pixel attack for fooling deep neural networkscited by 579
17 more
  1. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  2. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  3. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  4. 2018Deep Learning for Classical Japanese Literaturecited by 415
  5. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  6. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  7. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  8. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  9. 2021Improving Robustness using Generated Datacited by 233
  10. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  11. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  12. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 156
  13. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  14. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  15. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  16. 2019Image Super-Resolution as a Defense Against Adversarial Attackscited by 64
  17. 2018Defense-VAE: A Fast and Accurate Defense against Adversarial Attackscited by 9

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attackcited by 1
  2. 2025DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defensecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
  2. 2024DiffBreak: Is Diffusion-Based Purification Robust?
  3. 2024Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
  4. 2025Diffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial Purifier
  5. 2026A Low-Rank Defense Method for Adversarial Attack on Diffusion Models
  6. 2025Towards more transferable adversarial attack in black-box manner
  7. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
  8. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purification