mlsanityData to 7 Oct 2026

ADBM: Adversarial diffusion bridge model for reliable adversarial purification

arXiv 2408.00315 ↗First posted 1 Aug 2024cs.LG cs.AI cs.CVcited by 24

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

Abstract (arXiv)

Recently Diffusion-based Purification (DiffPure) has been recognized as an effective defense method against adversarial examples. However, we find DiffPure which directly employs the original pre-trained diffusion models for adversarial purification, to be suboptimal. This is due to an inherent trade-off between noise purification performance and data recovery quality. Additionally, the reliability of existing evaluations for DiffPure is questionable, as they rely on weak adaptive attacks. In this work, we propose a novel Adversarial Diffusion Bridge Model, termed ADBM. ADBM directly constructs a reverse bridge from the diffused adversarial data back to its original clean examples, enhancing the purification capabilities of the original diffusion models. Through theoretical analysis and experimental validation across various scenarios, ADBM has proven to be a superior and robust defense mechanism, offering significant promise for practical applications.

Key facts. Cited by 24 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 57 of its 67 references that are in the map. First posted on arXiv 1 Aug 2024.

Builds on

57 of 67 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness28 Oct
  2. 2023Enhancing Adversarial Robustness via Score-Based Optimization10 Jul
  3. 2023Robust Classification via a Single Diffusion Model24 May
  4. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attack14 May
  5. 2023Better Diffusion Models Further Improve Adversarial Training9 Feb
  6. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples9 Feb
  7. 2022(Certified!!) Adversarial Robustness for Free!21 Jun
  8. 2022Guided Diffusion Model for Adversarial Purification30 May
  9. 2022Diffusion Models for Adversarial Purification16 May
  10. 2021Adversarial purification with Score-based generative models11 Jun

Other references · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  10. 2013Intriguing properties of neural networkscited by 5,114
  11. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  12. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
35 more
  1. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  2. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  7. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  9. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  10. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  11. 2019Adversarial Examples Improve Image Recognitioncited by 283
  12. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  13. 2021Improving Robustness using Generated Datacited by 233
  14. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  15. 2021Data Augmentation Can Improve Robustnesscited by 193
  16. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  17. 2023Denoising Diffusion Bridge Modelscited by 171
  18. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  19. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 94
  20. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  21. 2020Patch-wise Attack for Fooling Deep Neural Networkcited by 78
  22. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  23. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  24. 2022A Light Recipe to Train Robust Vision Transformerscited by 64
  25. 2019The Limitations of Adversarial Training and the Blind-Spot Attackcited by 63
  26. 2024Diffusion Bridge Implicit Modelscited by 47
  27. 2021Online Adversarial Purification based on Self-Supervisioncited by 45
  28. 2022Natural Color Fool: Towards Boosting Black-box Unrestricted Attackscited by 38
  29. 2023Language-Driven Anchors for Zero-Shot Adversarial Robustnesscited by 23
  30. 2022On the Limitations of Stochastic Pre-processing Defensescited by 21
  31. 2024Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalizationcited by 15
  32. 2022On the Privacy Effect of Data Enhancement via the Lens of Memorizationcited by 14
  33. 2023On the Importance of Backbone to the Adversarial Robustness of Object Detectorscited by 12
  34. 2022Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samplescited by 11
  35. 2024PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognitioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 9.

24 papers.

Sort:

By area:

  1. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safetycited by 63
  2. 2024Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Modelscited by 23
  3. 2025Towards the Worst-case Robustness of Large Language Modelscited by 7
  4. 2025Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyondcited by 6
  5. 2026Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoningcited by 4
  6. 2025PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detectioncited by 3
  7. 2025Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreakingcited by 2
  8. 2025FlowPure: Continuous Normalizing Flows for Adversarial Purificationcited by 2
  9. 2024DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorizationcited by 1
  10. 2025Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Datasetcited by 1
  11. 2025Defending Against Frequency-Based Attacks with Diffusion Modelscited by 1
  12. 2025Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometrycited by 1
12 more
  1. 2025Do Concept Replacement Techniques Really Erase Unacceptable Concepts?cited by 1
  2. 2025DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purificationcited by 1
  3. 2025What is Adversarial Training for Diffusion Models?cited by 0
  4. 2025Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddingscited by 0
  5. 2026PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotationscited by 0
  6. 2026VocalBridge: Latent Diffusion-Bridge Purification for Defeating Perturbation-Based Voiceprint Defensescited by 0
  7. 2026Feature-Space Smoothing: Certified Robustness of Deep Representationscited by 0
  8. 2026PurSAMERE: Reliable Adversarial Purification via Sharpness-Aware Minimization of Expected Reconstruction Errorcited by 0
  9. 2026Expanding the Role of Diffusion Models for Robust Classifier Trainingcited by 0
  10. 2026Complementary Text-Guided Attention for Zero-Shot Adversarial Robustnesscited by 0
  11. 2026Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluationscited by 0
  12. 2026TARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as Purifierscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024LoRID: Low-Rank Iterative Diffusion for Adversarial Purification
  2. 2022Guided Diffusion Model for Adversarial Purification from Random Noise
  3. 2026NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
  4. 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
  5. 2025Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
  6. 2024Adversarial Guided Diffusion Models for Adversarial Purification
  7. 2025Towards more transferable adversarial attack in black-box manner
  8. 2024Instant Adversarial Purification with Adversarial Consistency Distillation