Model Synthesis for Zero-Shot Model Attribution

TL;DR

This paper introduces a zero-shot model attribution method using synthetic model generation to identify fingerprints of unseen generative models, significantly improving accuracy over existing static classifiers.

Contribution

It develops a novel synthesis-based fingerprint extractor that generalizes to unseen models without prior exposure, addressing limitations of static classifiers.

Findings

Achieves over 40% improvement in model identification accuracy on unseen models.

Improves verification accuracy by more than 15% on new models.

Demonstrates effective zero-shot generalization across diverse real-world generative models.

Abstract

Nowadays, generative models are shaping various fields such as art, design, and human-computer interaction, yet accompanied by challenges related to copyright infringement and content management. In response, existing research seeks to identify the unique fingerprints on the images they generate, which can be leveraged to attribute the generated images to their source models. Existing methods, however, are constrained to identifying models within a static set included in the classifier training, failing to adapt to newly emerged unseen models dynamically. To bridge this gap, we aim to develop a generalized model fingerprint extractor capable of zero-shot attribution, effectively attributes unseen models without exposure during training. Central to our method is a model synthesis technique, which generates numerous synthetic models mimicking the fingerprint patterns of real-world generative models. The design of the synthesis technique is motivated by observations on how the basic generative model's architecture building blocks and parameters influence fingerprint patterns, and it is validated through two designed metrics that examine synthetic models' fidelity and diversity. Our experiments demonstrate that this fingerprint extractor, trained solely on synthetic models, achieves impressive zero-shot generalization on a wide range of real-world generative models, improving model identification and verification accuracy on unseen models by over 40% and 15%, respectively, compared to existing approaches.