Proof-of-Authorship for Diffusion-based AI Generated Content

TL;DR

This paper introduces a cryptographic proof-of-authorship method for diffusion-based AI generated content, enabling creators to assert genuine authorship by binding the seed used in generation to their identity, with a probabilistic adjudicator assessing claim validity.

Contribution

It presents a novel proof-of-authorship framework for diffusion models that does not rely on secret information and uses cryptographic techniques to verify authorship claims.

Findings

The framework effectively distinguishes genuine authorship in case studies.

It can quantify the probability of false claims with a probabilistic adjudicator.

Analysis shows robustness against various attack scenarios.

Abstract

Recent advancements in AI-generated content (AIGC) have introduced new challenges in intellectual property protection and the authentication of generated objects. We focus on scenarios in which an author seeks to assert authorship of an object generated using latent diffusion models (LDMs), in the presence of adversaries who attempt to falsely claim authorship of objects they did not create. While proof-of-ownership has been studied in the context of multimedia content through techniques such as time-stamping and watermarking, these approaches face notable limitations. In contrast to traditional content creation sources (e.g., cameras), the LDM generation process offers greater control to the author. Specifically, the random seed used during generation can be deliberately chosen. By binding the seed to the author's identity using cryptographic pseudorandom functions, the author can assert to be the creator of the object. We refer to this stronger guarantee as proof-of-authorship, since only the creator of the object can legitimately claim the object. This contrasts with proof-of-ownership via time-stamping or watermarking, where any entity could potentially claim ownership of an object by being the first to timestamp or embed the watermark. We propose a proof-of-authorship framework involving a probabilistic adjudicator who quantifies the probability that a claim is false. Furthermore, unlike prior approaches, the proposed framework does not involve any secret. We explore various attack scenarios and analyze design choices using Stable Diffusion 2.1 (SD2.1) as representative case studies.