A Dual-Protection Framework for Copyright Protection and Image Editing Using Multi-Label Conformal Prediction

ICLR 2026 Conference Submission18246 Authors

Keywords: Diffusion Models, Copyright Protection, Conformal Inference, Invisible Watermarking

Abstract: Recent advances in diffusion models have significantly enhanced image editing capabilities, raising serious concerns about copyright protection. Traditional watermarks often fail to withstand diffusion-based edits, making image protection challenging. To address this, we propose a method that embeds an imperceptible perturbation in images, serving as a watermark while simultaneously disrupting the output of latent diffusion models. Our method employs a Score Estimator trained on select latent embeddings to embed the watermark by minimizing the score function. We then apply conformal inference to compute p-values for watermark detection. To distort the output of latent diffusion models, we shift watermarked image embeddings away from the distribution mean, distorting unauthorized generations. Experiments demonstrate our framework's superior performance in watermark detection, imperceptibility, and distortion efficacy, offering a comprehensive approach to protect images against latent diffusion models.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 18246