mlsanityData to 7 Oct 2026

DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purification

arXiv 2508.00552 ↗First posted 1 Aug 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Recent advances in deep neural networks (DNNs) have led to remarkable success across a wide range of tasks. However, their susceptibility to adversarial perturbations remains a critical vulnerability. Existing diffusion-based adversarial purification methods often require intensive iterative denoising, severely limiting their practical deployment. In this paper, we propose Diffusion Bridge Distillation for Purification (DBLP), a novel and efficient diffusion-based framework for adversarial purification. Central to our approach is a new objective, noise bridge distillation, which constructs a principled alignment between the adversarial noise distribution and the clean data distribution within a latent consistency model (LCM). To further enhance semantic fidelity, we introduce adaptive semantic enhancement, which fuses multi-scale pyramid edge maps as conditioning input to guide the purification process. Extensive experiments across multiple datasets demonstrate that DBLP achieves state-of-the-art (SOTA) robust accuracy, superior image quality, and around 0.2s inference time, marking a significant step toward real-time adversarial purification.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 54 of its 78 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

54 of 78 references.

References · 54

  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. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  11. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  12. 2013Intriguing properties of neural networkscited by 5,114
38 more
  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2016Wide Residual Networkscited by 3,057
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  5. 2022Video Diffusion Modelscited by 2,280
  6. 2023Consistency Modelscited by 1,778
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  9. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  10. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  11. 2022Diffusion Models for Adversarial Purificationcited by 469
  12. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  13. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  14. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  15. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  16. 2021Improving Robustness using Generated Datacited by 233
  17. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Modulecited by 211
  18. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  19. 2021Data Augmentation Can Improve Robustnesscited by 193
  20. 2019Adversarial Robustness through Local Linearizationcited by 146
  21. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  22. 2021Adversarial purification with Score-based generative modelscited by 132
  23. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  24. 2022Guided Diffusion Model for Adversarial Purificationcited by 90
  25. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  26. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  27. 2023Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilitycited by 66
  28. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  29. 2022Guided Diffusion Model for Adversarial Purification from Random Noisecited by 34
  30. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purificationcited by 24
  31. 2024MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsificationcited by 20
  32. 2023Enhancing Adversarial Robustness via Score-Based Optimizationcited by 19
  33. 2024Boosting Latent Diffusion with Perceptual Objectivescited by 19
  34. 2023MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Modelcited by 18
  35. 2024Instant Adversarial Purification with Adversarial Consistency Distillationcited by 14
  36. 2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
  37. 2023Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomnesscited by 13
  38. 2021Interpolated Joint Space Adversarial Training for Robust and Generalizable Defensescited by 10

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026VOID: Defeating Unauthorized Mimicry in Latent Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
  2. 2026NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
  3. 2025MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification
  4. 2024Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds
  5. 2026Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion
  6. 2024Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
  7. 2025Diffusion-based Cumulative Adversarial Purification for Vision Language Models
  8. 2024Random Sampling for Diffusion-based Adversarial Purification