mlsanityData to 7 Oct 2026

LoRID: Low-Rank Iterative Diffusion for Adversarial Purification

arXiv 2409.08255 ↗First posted 12 Sep 2024cs.LG cs.AI cs.CRcited by 7

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

Abstract (arXiv)

This work presents an information-theoretic examination of diffusion-based purification methods, the state-of-the-art adversarial defenses that utilize diffusion models to remove malicious perturbations in adversarial examples. By theoretically characterizing the inherent purification errors associated with the Markov-based diffusion purifications, we introduce LoRID, a novel Low-Rank Iterative Diffusion purification method designed to remove adversarial perturbation with low intrinsic purification errors. LoRID centers around a multi-stage purification process that leverages multiple rounds of diffusion-denoising loops at the early time-steps of the diffusion models, and the integration of Tucker decomposition, an extension of matrix factorization, to remove adversarial noise at high-noise regimes. Consequently, LoRID increases the effective diffusion time-steps and overcomes strong adversarial attacks, achieving superior robustness performance in CIFAR-10/100, CelebA-HQ, and ImageNet datasets under both white-box and black-box settings.

Key facts. Cited by 7 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 28 of its 45 references that are in the map. First posted on arXiv 12 Sep 2024.

Builds on

28 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification27 Oct
  2. 2023Better Diffusion Models Further Improve Adversarial Training9 Feb
  3. 2022Guided Diffusion Model for Adversarial Purification30 May

Other references · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2016Wide Residual Networkscited by 3,057
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  11. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  12. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
13 more
  1. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  2. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  3. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  4. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  5. 2021Improving Robustness using Generated Datacited by 233
  6. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  7. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  8. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 156
  9. 2023Robust Evaluation of Diffusion-Based Adversarial Purificationcited by 65
  10. 2020Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Modelscited by 58
  11. 2021Ensembling with Deep Generative Viewscited by 53
  12. 2019Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"cited by 12
  13. 2023Robust Adversarial Defense by Tensor Factorizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safetycited by 63
  2. 2025Diffusion-based Adversarial Purification from the Perspective of the Frequency Domaincited by 7
  3. 2025World Model Robustness via Surprise Recognitioncited by 3
  4. 2025DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purificationcited by 1
  5. 2025Keep It Real: Challenges in Attacking Compression-Based Adversarial Purificationcited by 0
  6. 2026Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusioncited by 0
  7. 2026Feature-Space Smoothing: Certified Robustness of Deep Representationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Guided Diffusion Model for Adversarial Purification from Random Noise
  2. 2025Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
  3. 2026NADD: Amplifying Noise for Effective Diffusion-based Adversarial Purification
  4. 2022Diffusion Models for Adversarial Purification
  5. 2024ADBM: Adversarial diffusion bridge model for reliable adversarial purification
  6. 2024Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
  7. 2023MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
  8. 2025Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry