paper-with-me

홈 › Papers

What is Adversarial Training for Diffusion Models?

2025-05-27 · Briglia Maria Rosaria, Mujtaba Hussain Mirza, Giuseppe Lisanti, Iacopo Masi

We answer the question in the title, showing that adversarial training (AT) for diffusion models (DMs) fundamentally differs from classifiers: while AT in classifiers enforces output invariance, AT in DMs requires equivariance to keep the diffusion process aligned with the data distribution. AT is a way to enforce smoothness in the diffusion flow, improving robustness to outliers and corrupted data. Unlike prior art, our method makes no assumptions about the noise model and integrates seamlessly into diffusion training by adding random noise, similar to randomized smoothing, or adversarial noise, akin to AT. This enables intrinsic capabilities such as handling noisy data, dealing with extreme variability such as outliers, preventing memorization, and improving robustness. We rigorously evaluate our approach with proof-of-concept datasets with known distributions in low- and high-dimensional space, thereby taking a perfect measure of errors; we further evaluate on standard benchmarks such as CIFAR-10, CelebA and LSUN Bedroom, showing strong performance under severe noise, data corruption, and iterative adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2505.21742

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets

2023-03-10 · CVPR 2023 1 · Weixin Chen, Dawn Song, Bo Li

Diffusion models have achieved great success in a range of tasks, such as image synthesis and molecule design. As such successes hinge on large-scale training data collected from diverse sources, the trustworthiness of t…

Image Generation

Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination

2024-05-25 · Shelly Golan, Roy Ganz, Michael Elad

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis. These methods overcome the slowness of diffusion models by directly mappi…

Image Generation

Robust Classification via a Single Diffusion Model

2023-05-24 · Huanran Chen, Yinpeng Dong, Zhengyi Wang, Xiao Yang 외

Diffusion models have been applied to improve adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, diffusion-based purification c…

Adversarial DefenseAdversarial RobustnessClassificationmodel+1

Struggle with Adversarial Defense? Try Diffusion

2024-04-12 · Yujie Li, Yanbin Wang, Haitao Xu, Bin Liu 외

Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purif…

Adversarial DefenseAdversarial Robustness

Deceptive Diffusion: Generating Synthetic Adversarial Examples

2024-06-28 · Lucas Beerens, Catherine F. Higham, Desmond J. Higham

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassif…

Adversarial Attack