Responsible Disclosure of Generative Models Using Scalable Fingerprinting
This work addresses the problem of detecting and attributing deepfakes and misinformation generated by advanced generative models, which is a significant concern for society and the responsible development of AI.
This paper proposes a method for fingerprinting generative models to enable detection and attribution of generated samples. Their technique allows for an ad-hoc generation of a large population of models with distinct fingerprints, with a 128-bit fingerprint theoretically allowing for over 10^38 identifiable models.
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 .