# Responsible Disclosure of Generative Models Using Scalable Fingerprinting

arXiv: https://arxiv.org/abs/2012.08726 · HTML: https://mlsanity.com/paper/2012.08726/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2020.

## Built on by (most cited first, 30 of 91)

- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error](https://mlsanity.com/paper/2401.17879/) (2024)
- [TALL: Thumbnail Layout for Deepfake Video Detection](https://mlsanity.com/paper/2307.07494/) (2023)
- [Three Bricks to Consolidate Watermarks for Large Language Models](https://mlsanity.com/paper/2308.00113/) (2023)
- [Proactive Detection of Voice Cloning with Localized Watermarking](https://mlsanity.com/paper/2401.17264/) (2024)
- [Real-Time Radiance Fields for Single-Image Portrait View Synthesis](https://mlsanity.com/paper/2305.02310/) (2023)
- [R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model](https://mlsanity.com/paper/2405.16341/) (2024)
- [RoSteALS: Robust Steganography using Autoencoder Latent Space](https://mlsanity.com/paper/2304.03400/) (2023)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2306.04744/) (2023)
- [Watermark Anything with Localized Messages](https://mlsanity.com/paper/2411.07231/) (2024)
- [Leveraging Optimization for Adaptive Attacks on Image Watermarks](https://mlsanity.com/paper/2309.16952/) (2023)
- [Video Seal: Open and Efficient Video Watermarking](https://mlsanity.com/paper/2412.09492/) (2024)
- [Deepfake Network Architecture Attribution](https://mlsanity.com/paper/2202.13843/) (2022)
- [FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error](https://mlsanity.com/paper/2412.07140/) (2024)
- [Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis](https://mlsanity.com/paper/2105.14376/) (2021)
- [RepMix: Representation Mixing for Robust Attribution of Synthesized Images](https://mlsanity.com/paper/2207.02063/) (2022)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators](https://mlsanity.com/paper/2304.07361/) (2023)
- [A Watermark-Conditioned Diffusion Model for IP Protection](https://mlsanity.com/paper/2403.10893/) (2024)
- [Progressive Open Space Expansion for Open-Set Model Attribution](https://mlsanity.com/paper/2303.06877/) (2023)
- [Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives](https://mlsanity.com/paper/2311.09227/) (2023)
- [LaWa: Using Latent Space for In-Generation Image Watermarking](https://mlsanity.com/paper/2408.05868/) (2024)
- [How to Trace Latent Generative Model Generated Images without Artificial Watermark?](https://mlsanity.com/paper/2405.13360/) (2024)
- [UnMarker: A Universal Attack on Defensive Image Watermarking](https://mlsanity.com/paper/2405.08363/) (2024)
- [Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models](https://mlsanity.com/paper/2404.09401/) (2024)
- [Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection](https://mlsanity.com/paper/2403.10261/) (2024)
- [GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis](https://mlsanity.com/paper/2407.10471/) (2024)
- [Learning to Disentangle GAN Fingerprint for Fake Image Attribution](https://mlsanity.com/paper/2106.08749/) (2021)
- [Attributing Image Generative Models using Latent Fingerprints](https://mlsanity.com/paper/2304.09752/) (2023)

## Abstract (arXiv)

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 1038 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 .