mlsanityData to 14 Oct 2026

Improved Diffusion-based Generative Model with Better Adversarial Robustness

arXiv 2502.17099 ↗First posted 24 Feb 2025cs.LG cs.AI cs.CVcited by 3

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mismatch. During the denoising process, the input data distributions differ between the training and inference stages, potentially leading to inaccurate data generation. To obviate this, we analyze the training objective of DPMs and theoretically demonstrate that this mismatch can be alleviated through Distributionally Robust Optimization (DRO), which is equivalent to performing robustness-driven Adversarial Training (AT) on DPMs. Furthermore, for the recently proposed Consistency Model (CM), which distills the inference process of the DPM, we prove that its training objective also encounters the mismatch issue. Fortunately, this issue can be mitigated by AT as well. Based on these insights, we propose to conduct efficient AT on both DPM and CM. Finally, extensive empirical studies validate the effectiveness of AT in diffusion-based models. The code is available at https://github.com/kugwzk/AT_Diff.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 58 of its 74 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

58 of 74 references.

Closest ancestors · 25

Same direction, newest first

  1. 2024Accelerating Diffusion Sampling with Optimized Time Steps27 Feb
  2. 2024The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling23 Feb
  3. 2023One-step Diffusion with Distribution Matching Distillation30 Nov
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  5. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  6. 2023SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models10 Sep
  7. 2023Elucidating the Exposure Bias in Diffusion Models29 Aug
  8. 2023On Error Propagation of Diffusion Models9 Aug
  9. 2023Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models15 Jun
  10. 2023Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps24 May
  11. 2023On the Generalization of Diffusion Model24 May
  12. 2023Reflected Diffusion Models10 Apr
13 more
  1. 2023Consistency Models2 Mar
  2. 2023Input Perturbation Reduces Exposure Bias in Diffusion Models27 Jan
  3. 2022Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions3 Nov
  4. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions22 Sep
  5. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  6. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  11. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  12. 2020Denoising Diffusion Implicit Models6 Oct
  13. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  12. 2022Video Diffusion Modelscited by 2,305
21 more
  1. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  2. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  3. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  4. 2019Adversarial Training for Free!cited by 643
  5. 2015Sequence Level Training with Recurrent Neural Networkscited by 576
  6. 2016Self-critical Sequence Training for Image Captioningcited by 547
  7. 2022Diffusion Models for Adversarial Purificationcited by 476
  8. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  9. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 264
  10. 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 254
  11. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
  12. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 204
  13. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
  14. 2019Classification Accuracy Score for Conditional Generative Modelscited by 136
  15. 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
  16. 2015Minimum Risk Training for Neural Machine Translationcited by 115
  17. 2021Improved OOD Generalization via Adversarial Training and Pre-trainingcited by 66
  18. 2024Towards Understanding the Working Mechanism of Text-to-Image Diffusion Modelcited by 48
  19. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  20. 2023Enhancing Adversarial Robustness via Score-Based Optimizationcited by 19
  21. 2022Breaking Correlation Shift via Conditional Invariant Regularizercited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Elucidating the SNR-t Bias of Diffusion Probabilistic Modelscited by 3
  2. 2026Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Imagescited by 1
  3. 2026OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Mannercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Improving Adversarial Robustness by Contrastive Guided Diffusion Process
  2. 2022Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
  3. 2025What is Adversarial Training for Diffusion Models?
  4. 2021Improved Denoising Diffusion Probabilistic Models
  5. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models
  6. 2023Efficient Transfer Learning in Diffusion Models via Adversarial Noise
  7. 2022Few-shot Image Generation with Diffusion Models
  8. 2024ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation