mlsanityData to 7 Oct 2026

Guided Diffusion Model for Adversarial Purification from Random Noise

arXiv 2206.10875 ↗First posted 22 Jun 2022cs.LG cs.CRcited by 34

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

Abstract (arXiv)

In this paper, we propose a novel guided diffusion purification approach to provide a strong defense against adversarial attacks. Our model achieves 89.62% robust accuracy under PGD-L_inf attack (eps = 8/255) on the CIFAR-10 dataset. We first explore the essential correlations between unguided diffusion models and randomized smoothing, enabling us to apply the models to certified robustness. The empirical results show that our models outperform randomized smoothing by 5% when the certified L2 radius r is larger than 0.5.

Key facts. Cited by 34 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 17 of its 18 references that are in the map. First posted on arXiv 22 Jun 2022.

Builds on

17 of 18 references.

Closest ancestors · 3

Same direction, newest first

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

Other references · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2013Auto-Encoding Variational Bayescited by 3,980
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  12. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
2 more
  1. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211
  2. 2020Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Modelscited by 58

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 17; 2024: 12; 2025: 3; 2026: 1.

34 papers.

Sort:

By area:

  1. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 198
  2. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 72
  3. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  4. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  5. 2023Class-Balancing Diffusion Modelscited by 47
  6. 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purificationcited by 36
  7. 2022DensePure: Understanding Diffusion Models towards Adversarial Robustnesscited by 33
  8. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 21
  9. 2023Enhancing Adversarial Robustness via Score-Based Optimizationcited by 19
  10. 2023Accelerating Guided Diffusion Sampling with Splitting Numerical Methodscited by 13
  11. 2023Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomnesscited by 13
  12. 2023Semantic Adversarial Attacks via Diffusion Modelscited by 12
22 more
  1. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  2. 2024Adversarial Guided Diffusion Models for Adversarial Purificationcited by 8
  3. 2024Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspectivecited by 8
  4. 2023Salient Conditional Diffusion for Defending Against Backdoor Attackscited by 7
  5. 2023Diffusion models meet image counter-forensicscited by 6
  6. 2024DiffBreak: Is Diffusion-Based Purification Robust?cited by 6
  7. 2024Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Informationcited by 5
  8. 2023Time Series Diffusion Method: A Denoising Diffusion Probabilistic Model for Vibration Signal Generationcited by 4
  9. 2024CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defensecited by 4
  10. 2023Diffusion Sampling with Momentum for Mitigating Divergence Artifactscited by 3
  11. 2025LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attackscited by 3
  12. 2023DiffDefense: Defending against Adversarial Attacks via Diffusion Modelscited by 2
  13. 2023Asymmetric Diffusion Based Channel-Adaptive Secure Wireless Semantic Communicationscited by 2
  14. 2024Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustnesscited by 2
  15. 2024Efficient Image-to-Image Diffusion Classifier for Adversarial Robustnesscited by 2
  16. 2024Diffusion-based Adversarial Purification for Intrusion Detectioncited by 1
  17. 2024Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Costcited by 1
  18. 2025DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purificationcited by 1
  19. 2023Adversarial defense based on distribution transfercited by 0
  20. 2024RCDM: Enabling Robustness for Conditional Diffusion Modelcited by 0
  21. 2025Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusioncited by 0
  22. 2026Generative AI and Federated Learning for Intrusion Detection Systems: A Surveycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LoRID: Low-Rank Iterative Diffusion for Adversarial Purification
  2. 2025Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry
  3. 2026NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
  4. 2025Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
  5. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purification
  6. 2025Defending Against Frequency-Based Attacks with Diffusion Models
  7. 2024Random Sampling for Diffusion-based Adversarial Purification
  8. 2025Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off