Lune

USENIX Security2025Top-tier venue

Watch the Watchers! On the Security Risks of Robustness-Enhancing Diffusion Models

Changjiang Li, Ren Pang, Bochuan Cao, Jinghui Chen, Fenglong Ma, Shouling Ji, Ting Wang

Abstract

Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the robustness of other models, notably in purifying adversarial examples and certifying adversarial robustness. However, the potential risks of these practices remain largely unexplored, which is highly concerning. To bridge this gap, this work investigates the vulnerability of robustnessenhancing diffusion models. Specifically, we demonstrate that these models are highly susceptible to DIFF2, a simple yet effective attack, which substantially diminishes their robustness assurance. Essentially, DIFF2 integrates a malicious diffusion-sampling process into the diffusion model, guiding inputs embedded with specific triggers toward an adversarydefined distribution while preserving the normal functionality for clean inputs. Our case studies on adversarial purification and robustness certification show that DIFF2 can significantly reduce both post-purification and certified accuracy across benchmark datasets and models, highlighting the potential risks of relying on pre-trained diffusion models as defensive tools. We further explore possible countermeasures, suggesting promising avenues for future research.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • High-Resolution Image Synthesis with Latent Diffusion Models cites Diffusion Models Beat GANs on Image Synthesis
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Implicit Models
  • Diffusion Models Beat GANs on Image Synthesis cites Denoising Diffusion Probabilistic Models
  • Diffusion Models Beat GANs on Image Synthesis cites Denoising Diffusion Implicit Models
  • Denoising Diffusion Implicit Models cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on40

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
  3. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  4. Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
  5. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacksFrancesco Croce, Matthias HeinICML 2020 · 2,337 citations

Related papers

  1. DensePure: Understanding Diffusion Models for Adversarial RobustnessChaowei Xiao, Zhongzhu Chen, Kun Jin, Jiongxiao Wang et al.ICLR 2023 · 18 citations
  2. DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local SmoothingJiawei Zhang, Zhongzhu Chen, Huan Zhang, Chaowei Xiao et al.USENIX Security 2023
  3. Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic PerspectiveYiming Liu, Kezhao Liu, Yao Xiao, Ziyi Dong et al.ICLR 2025
  4. Robust Evaluation of Diffusion-Based Adversarial PurificationMinjong Lee, Dongwoo KimICCV 2023 · 96 citations
  5. ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial PurificationXiao Li, Wenxuan Sun, Huanran Chen, Qiongxiu Li et al.ICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines