Responsible Disclosure of Generative Models Using Scalable Fingerprinting

TL;DR

This paper introduces a scalable fingerprinting method for generative models, enabling model attribution and deep fake detection by embedding unique 128-bit identifiers, addressing concerns of misuse and model provenance.

Contribution

The work presents a novel scalable fingerprinting technique for generative models, allowing for efficient creation of numerous uniquely identifiable models.

Findings

Achieves effective deep fake detection and attribution.

Supports over 10^38 distinct identifiable models.

Fulfills key properties of a robust fingerprinting mechanism.

Abstract

Over the past years, deep generative models have achieved a new level of performance. Generated data has become difficult, if not impossible, to be distinguished from real data. While there are plenty of use cases that benefit from this technology, there are also strong concerns on how this new technology can be misused to generate deep fakes and enable misinformation at scale. Unfortunately, current deep fake detection methods are not sustainable, as the gap between real and fake continues to close. In contrast, our work enables a responsible disclosure of such state-of-the-art generative models, that allows model inventors to fingerprint their models, so that the generated samples containing a fingerprint can be accurately detected and attributed to a source. Our technique achieves this by an efficient and scalable ad-hoc generation of a large population of models with distinct fingerprints. Our recommended operation point uses a 128-bit fingerprint which in principle results in more than $10^{38}$ identifiable models. Experiments show that our method fulfills key properties of a fingerprinting mechanism and achieves effectiveness in deep fake detection and attribution. Code and models are available at https://github.com/ningyu1991/ScalableGANFingerprints .