VAGUEGAN: Stealthy Poisoning and Backdoor Attacks on Image Generative Pipelines
This exposes a blind spot in defenses for image generation pipelines, raising integrity concerns, but it is incremental as it builds on existing adversarial attack methods.
The paper tackles the problem of stealthy poisoning and backdoor attacks on image generative pipelines, introducing VagueGAN to craft triggers that cause targeted changes in generated images while showing that poisoned outputs can have higher visual quality than clean ones.
Generative models such as GANs and diffusion models are widely used to synthesize photorealistic images and to support downstream creative and editing tasks. While adversarial attacks on discriminative models are well studied, attacks targeting generative pipelines where small, stealthy perturbations in inputs lead to controlled changes in outputs are less explored. This study introduces VagueGAN, an attack pipeline combining a modular perturbation network PoisonerNet with a Generator Discriminator pair to craft stealthy triggers that cause targeted changes in generated images. Attack efficacy is evaluated using a custom proxy metric, while stealth is analyzed through perceptual and frequency domain measures. The transferability of the method to a modern diffusion based pipeline is further examined through ControlNet guided editing. Interestingly, the experiments show that poisoned outputs can display higher visual quality compared to clean counterparts, challenging the assumption that poisoning necessarily reduces fidelity. Unlike conventional pixel level perturbations, latent space poisoning in GANs and diffusion pipelines can retain or even enhance output aesthetics, exposing a blind spot in pixel level defenses. Moreover, carefully optimized perturbations can produce consistent, stealthy effects on generator outputs while remaining visually inconspicuous, raising concerns for the integrity of image generation pipelines.