Diffusion-C: Unveiling the Generative Challenges of Diffusion Models through Corrupted Data
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
In our contemporary academic inquiry, we present "Diffusion-C," a foundational methodology to analyze the generative restrictions of Diffusion Models, particularly those akin to GANs, DDPM, and DDIM. By employing input visual data that has been subjected to a myriad of corruption modalities and intensities, we elucidate the performance characteristics of those Diffusion Models. The noise component takes center stage in our analysis, hypothesized to be a pivotal element influencing the mechanics of deep learning systems. In our rigorous expedition utilizing Diffusion-C, we have discerned the following critical observations: (I) Within the milieu of generative models under the Diffusion taxonomy, DDPM emerges as a paragon, consistently exhibiting superior performance metrics. (II) Within the vast spectrum of corruption frameworks, the fog and fractal corruptions notably undermine the functional robustness of both DDPM and DDIM. (III) The vulnerability of Diffusion Models to these particular corruptions is significantly influenced by topological and statistical similarities, particularly concerning the alignment between mean and variance. This scholarly work highlights Diffusion-C's core understandings regarding the impacts of various corruptions, setting the stage for future research endeavors in the realm of generative models.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 20 of its 27 references that are in the map. First posted on arXiv 14 Dec 2023.
Builds on
20 of 27 references.
Closest ancestors · 7
Same direction, newest first
- 2022Soft Diffusion: Score Matching for General Corruptions12 Sep
- 2022Diffusion Models in Vision: A Survey10 Sep
- 2022gDDIM: Generalized denoising diffusion implicit models11 Jun
- 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
- 2021Non Gaussian Denoising Diffusion Models14 Jun
- 2020Denoising Diffusion Implicit Models6 Oct
- 2020Denoising Diffusion Probabilistic Models19 Jun
Other references · 13
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
- 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 256
- 2023Membership Inference Attacks against Diffusion Modelscited by 84
- 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusioncited by 75
- 2020Opportunities and Challenges in Deep Learning Adversarial Robustness: A Surveycited by 71
- 2022Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentationcited by 55
- 2022Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Modelscited by 44
1 more
- 2023Defending against Adversarial Audio via Diffusion Modelcited by 20
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Adversarial Examples are Misaligned in Diffusion Model Manifolds
- 2022Diffusion Models: A Comprehensive Survey of Methods and Applications
- 2024Diffusion Models in Low-Level Vision: A Survey
- 2025Deeper Diffusion Models Amplify Bias
- 2022Towards the Detection of Diffusion Model Deepfakes
- 2022Progressive Distillation for Fast Sampling of Diffusion Models
- 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Models
- 2025Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control