# Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models

arXiv: https://arxiv.org/abs/2406.09669 · HTML: https://mlsanity.com/paper/2406.09669/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 48 of its 66 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Maximum Likelihood Training of Score-Based Diffusion Models](https://mlsanity.com/paper/2101.09258/) (2021)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Certified Defenses against Adversarial Examples](https://mlsanity.com/paper/1801.09344/) (2018)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)

## Built on by (most cited first, 4 of 4)

- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models](https://mlsanity.com/paper/2504.05815/) (2025)
- [Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models](https://mlsanity.com/paper/2502.20650/) (2025)
- [Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Models](https://mlsanity.com/paper/2603.04064/) (2026)

## Abstract (arXiv)

Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial robustness. However, the security risks of these practices themselves remain largely unexplored, which is highly concerning. To bridge this gap, this work investigates the vulnerabilities of security-enhancing diffusion models. Specifically, we demonstrate that these models are highly susceptible to DIFF2, a simple yet effective backdoor attack, which substantially diminishes the security assurance provided by such models. Essentially, DIFF2 achieves this by integrating a malicious diffusion-sampling process into the diffusion model, guiding inputs embedded with specific triggers toward an adversary-defined 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.