VAGUEGAN: Stealthy Poisoning and Backdoor Attacks on Image Generative Pipelines
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clea…
Backdoor Attackbackdoor defenseVocal Bursts Valence PredictionSilent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor attacks. We propose a novel poisoning atta…
Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound
Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where…
Backdoor Attackspeech-recognitionSpeech RecognitionSilent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack
Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that operates in clean-label, black-box settin…
Backdoor AttackData PoisoningBackdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning
Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first syste…
Speech Emotion Recognition