Training-Free Watermarking for Autoregressive Image Generation

ICLR 2026 Conference Submission15766 Authors

Keywords: Image watermarking, Autoregressive Image Generation Model, VQ-VAE

TL;DR: This paper proposes the first training-free watermarking method for autoregressive image generation models.

Abstract: Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored. Moreover, direct application of LLM watermarking solutions may impair image diversity and compromise the imperceptibility of watermarks. To address these challenges, we propose IndexMark, a training-free watermarking framework for autoregressive image generation models. IndexMark is inspired by the redundancy property of the codebook: replacing autoregressively generated indices with similar indices produces negligible visual differences. The core component in IndexMark is a simple yet effective match-then-replace method, which carefully selects watermark tokens from the codebook based on token similarity, and promotes the use of watermark tokens through token replacement, thereby embedding the watermark without affecting the image diversity and quality. Watermark verification is achieved by calculating the proportion of watermark tokens in generated images, with precision further improved by an optional Index Encoder. Furthermore, we introduce an auxiliary validation scheme to enhance robustness against cropping attacks. Experiments demonstrate that IndexMark achieves state-of-the-art performance in terms of image quality and verification accuracy, and exhibits robustness against various perturbations, including cropping, noises, Gaussian blur, random erasing, color jittering, random rotation, and JPEG compression. Code will be made public.

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

Submission Number: 15766