arxiv6.0 / 10

PP-Mark: Provable and Publicly Verifiable Watermarking for Generative AI

Hankyeong Ko, Taehoon Kim

Abstract

Generative AI models now produce images indistinguishable from real data, making publicly verifiable provenance essential; however, existing watermarking methods become vulnerable to forgeries and adversarial optimization attacks once their detectors are made public. We propose PP-Mark, a provenance framework that anchors lightweight statistical detection to a zero-knowledge proof of the embedding process, ensuring that forged content cannot pass full verification by construction. We establish formal unforgeability under standard cryptographic assumptions and validate PP-Mark against representative baselines across two latent-diffusion models (SD2.1 and SDXL), demonstrating resistance to black-box imprint forgery, white-box optimization, and regeneration attacks while remaining practical for decentralized verification. Code is available at https://github.com/hko920920/PP-Mark_NeurIPS2026

Research area

adversarial robustnesssecuritywatermarking
Published
30 Oct 2026
Source
arxiv
Org
Sogang University
View paper
Sign in to read and join the discussion.