DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing
This addresses security concerns for users whose images are vulnerable to malicious edits, offering an incremental improvement over existing pixel-space defenses.
The paper tackles the problem of malicious image editing enabled by diffusion models by proposing a frequency-domain defense that modifies DCT coefficients, resulting in fewer visual artifacts while maintaining edit protection and robustness to purification techniques like JPEG compression.
Advancements in diffusion models have enabled effortless image editing via text prompts, raising concerns about image security. Attackers with access to user images can exploit these tools for malicious edits. Recent defenses attempt to protect images by adding a limited noise in the pixel space to disrupt the functioning of diffusion-based editing models. However, the adversarial noise added by previous methods is easily noticeable to the human eye. Moreover, most of these methods are not robust to purification techniques like JPEG compression under a feasible pixel budget. We propose a novel optimization approach that introduces adversarial perturbations directly in the frequency domain by modifying the Discrete Cosine Transform (DCT) coefficients of the input image. By leveraging the JPEG pipeline, our method generates adversarial images that effectively prevent malicious image editing. Extensive experiments across a variety of tasks and datasets demonstrate that our approach introduces fewer visual artifacts while maintaining similar levels of edit protection and robustness to noise purification techniques.