Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation

Aditya Desu, Xuanli He, Qiongkai Xu, Wei Lu

Abstract: As machine- and AI-generated content proliferates, protecting the intellectual property of generative models has become imperative, yet verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of generated data. Confirming the ownership of the data is challenging, as the data generation process is opaque to those verifying the authenticity. Our work is dedicated to detecting data reuse from a single sample. While watermarking has been the traditional method to detect AI-generated content by embedding specific information within models or their outputs, which could compromise the quality of outputs, our approach instead identifies inherent fingerprints in the outputs without altering models. The verification is achieved by requiring the (authentic) models to re-generate the data. Furthermore, we propose a method that iteratively re-generates the data to enhance these fingerprints in the generation stage. The strategy is both theoretically sound and empirically proven effective with recent advanced text and image generative models. Our approach is significant because it avoids extra operations or measures, such as (1) modifying model parameters, (2) altering the generated outputs, or (3) employing additional classification models for verification. This enhancement broadens the applicability of authorship verification (1) to track the IP violation in generative models published without explicitly designed watermark mechanisms and (2) to produce outputs without compromising their quality.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Makoto_Yamada3

Submission Number: 2445