StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model

Ziyin Zhou, Ke Sun, Zhongxi Chen, Huafeng Kuang, Xiaoshuai Sun, Rongrong Ji

Abstract:

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 demonstrate the effectiveness of StealthDiffusion in both white-box and black-box settings, transforming AI-generated images into higher-quality adversarial forgeries with frequency spectra resembling genuine images. These images are classified as genuine by state-of-the-art forensic classifiers and are difficult for humans to distinguish.

Primary Subject Area: [Generation] Social Aspects of Generative AI

Secondary Subject Area: [Experience] Art and Culture

Relevance To Conference: Provided a new adversarial algorithm for AIGC image to evade forensic classifier detection.

Submission Number: 454