# Diffusion Models are Robust Pretrainers

Source: [Diffusion Models are Robust Pretrainers](<https://www.sota2.com/research/paper/690ada075fbd5403840047f7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-06T05:03:43.312Z

Authors: Mika Yagoda, Shady Abu-Hussein, Raja Giryes

Published: 2025-11-04T18:16:04.000Z

## Abstract

Diffusion models have gained significant attention for high-fidelity image generation. Our work investigates the potential of exploiting diffusion models for adversarial robustness in image classification and object detection. Adversarial attacks challenge standard models in these tasks by perturbing inputs to force incorrect predictions. To address this issue, many approaches use training schemes for forcing the robustness of the models, which increase training costs. In this work, we study models built on top of off-the-shelf diffusion models and demonstrate their practical significance: they provide a low-cost path to robust representations, allowing lightweight heads to be trained on frozen features without full adversarial training. Our empirical evaluations on ImageNet, CIFAR-10, and PASCAL VOC show that diffusion-based classifiers and detectors achieve meaningful adversarial robustness with minimal compute. While clean and adversarial accuracies remain below state-of-the-art adversarially trained CNNs or ViTs, diffusion pretraining offers a favorable tradeoff between efficiency and robustness. This work opens a promising avenue for integrating diffusion models into resource-constrained robust deployments.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.02793>)

[PDF](<https://arxiv.org/pdf/2511.02793.pdf>)
