DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders
2026-07-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors explain that AI systems often use people’s photos from the internet without permission, which can invade privacy. To stop this, they create special images called unlearnable examples that hide useful info from AI by adding tiny changes. Their new method, DiffUE, changes the image’s deeper meaning instead of just the pixels, making it harder for AI to learn from the images while keeping them looking natural. Tests showed DiffUE works better than older methods in balancing image quality and privacy protection.
unlearnable examplesdiffusion-based autoencodersemantic spacepixel-space noiseadversarial trainingimage transformationimage compressionprivacy protectionfacial recognitionimage utility
Authors
Syed Irfan Ali Meerza, Oktay Ozturk, Amir Sadovnik, Jian Liu
Abstract
AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising. To counter this, researchers have developed unlearnable examples (UEs), images modified with imperceptible noise to prevent AI models from extracting meaningful information. However, existing UE methods primarily rely on pixel-space noise, which can be bypassed by relearning strategies such as adversarial training, image transformation, and compression. While some techniques improve robustness, they often come at the expense of significant degradation in image utility and perceptual quality. In this paper, we introduce DiffUE to overcome these limitations by injecting noise into the semantic space of images instead of the pixel space. Instead of corrupting pixel values, DiffUE modifies high-level semantic features of images, ensuring robust unlearnability while preserving visual quality and utility. By leveraging a diffusion-based autoencoder framework to manipulate semantic features, DiffUE generates purposeful, natural-looking modifications that effectively resist advanced relearning strategies. Extensive experiments on four datasets, CIFAR-10, CIFAR-100, CelebA-HQ, and ImageNet, as well as a subjective user study, demonstrate that DiffUE significantly enhances the trade-off between image quality and unlearnability, offering a more robust and effective solution for safeguarding personal data in an increasingly exploitative AI landscape.