Watermarking Autoregressive Image Generation
This addresses the need for tracking misuse in autoregressive image generation, though it is incremental as it adapts existing techniques to a new domain.
The paper tackles the problem of watermarking autoregressive image generation models to track provenance, introducing the first token-level approach that adapts language model watermarking and addresses reverse cycle-consistency challenges, resulting in reliable and robust detection with theoretically grounded p-values.
Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted to watermark their outputs at the token level. In this work, we present the first such approach by adapting language model watermarking techniques to this setting. We identify a key challenge: the lack of reverse cycle-consistency (RCC), wherein re-tokenizing generated image tokens significantly alters the token sequence, effectively erasing the watermark. To address this and to make our method robust to common image transformations, neural compression, and removal attacks, we introduce (i) a custom tokenizer-detokenizer finetuning procedure that improves RCC, and (ii) a complementary watermark synchronization layer. As our experiments demonstrate, our approach enables reliable and robust watermark detection with theoretically grounded p-values. Code and models are available at https://github.com/facebookresearch/wmar.