# StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model

arXiv: https://arxiv.org/abs/2408.05669 · HTML: https://mlsanity.com/paper/2408.05669/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 11 Aug 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [Generalizing Face Forgery Detection with High-frequency Features](https://mlsanity.com/paper/2103.12376/) (2021)
- [Fourier Spectrum Discrepancies in Deep Network Generated Images](https://mlsanity.com/paper/1911.06465/) (2019)
- [Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection](https://mlsanity.com/paper/2103.09096/) (2021)
- [Intriguing properties of synthetic images: from generative adversarial networks to diffusion models](https://mlsanity.com/paper/2304.06408/) (2023)
- [Towards the Detection of Diffusion Model Deepfakes](https://mlsanity.com/paper/2210.14571/) (2022)
- [Dual Contrastive Learning for General Face Forgery Detection](https://mlsanity.com/paper/2112.13522/) (2021)
- [Diffusion Models for Imperceptible and Transferable Adversarial Attack](https://mlsanity.com/paper/2305.08192/) (2023)
- [A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection](https://mlsanity.com/paper/2103.17195/) (2021)
- [On the Frequency Bias of Generative Models](https://mlsanity.com/paper/2111.02447/) (2021)
- [Evading DeepFake Detectors via Adversarial Statistical Consistency](https://mlsanity.com/paper/2304.11670/) (2023)
- [DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis](https://mlsanity.com/paper/2403.18471/) (2024)
- [Continual Face Forgery Detection via Historical Distribution Preserving](https://mlsanity.com/paper/2308.06217/) (2023)

## Built on by (most cited first, 12 of 12)

- [Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges](https://mlsanity.com/paper/2502.19716/) (2025)
- [ForensicConcept: Transferable Forensic Concepts for AIGI Detection](https://mlsanity.com/paper/2606.07034/) (2026)
- [Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective](https://mlsanity.com/paper/2505.22604/) (2025)
- [Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidance](https://mlsanity.com/paper/2602.06530/) (2026)
- [Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cues](https://mlsanity.com/paper/2602.12381/) (2026)
- [Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models](https://mlsanity.com/paper/2411.08642/) (2024)
- [A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement](https://mlsanity.com/paper/2506.23676/) (2025)
- [Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems](https://mlsanity.com/paper/2507.21157/) (2025)
- [FBA2D: Frequency-based Black-box Attack for AI-generated Image Detection](https://mlsanity.com/paper/2512.09264/) (2025)
- [Multi-Feature Fusion Approach for Generative AI Images Detection](https://mlsanity.com/paper/2603.29788/) (2026)
- [ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors](https://mlsanity.com/paper/2607.21897/) (2026)
- [TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors](https://mlsanity.com/paper/2607.25894/) (2026)

## Abstract (arXiv)

The rapid progress in generative models has given rise to the critical task of AI-Generated Content Stealth (AIGC-S), which aims to create AI-generated images that can evade both forensic detectors and human inspection. This task is crucial for understanding the vulnerabilities of existing detection methods and developing more robust techniques. However, current adversarial attacks often introduce visible noise, have poor transferability, and fail to address spectral differences between AI-generated and genuine images. To address this, we propose StealthDiffusion, a framework based on stable diffusion that modifies AI-generated images into high-quality, imperceptible adversarial examples capable of evading state-of-the-art forensic detectors. StealthDiffusion comprises two main components: Latent Adversarial Optimization, which generates adversarial perturbations in the latent space of stable diffusion, and Control-VAE, a module that reduces spectral differences between the generated adversarial images and genuine images without affecting the original diffusion model's generation process. Extensive experiments show that StealthDiffusion is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries with frequency spectra similar to genuine images. These forgeries are classified as genuine by advanced forensic classifiers and are difficult for humans to distinguish.