Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

By Ning Yu, Vladislav Skripniuk, Sahar Abdelnabi, Mario Fritz. 2020

322 citations recorded by the source corpus.

Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs). Yet, the dark side of such deepfakes, the malicious use of generated media, raises concerns about visual misinformation. While existing research work on deepfake detection demonstrates high accuracy, it is subject to advances in generation techniques and adversarial iterations on detection countermeasure techniques. Thus, we seek a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models.Our approach is simple and effective. We first embed artificial fingerprints into training data, then validate a surprising discovery on the transferability of such fingerprints from training data to generative models, which in turn appears in the generated deepfakes. Experiments show that our fingerprinting solution (1) holds for a variety of cutting-edge generative models, (2) leads to a negligible side effect on generation quality, (3) stays robust against image-level and model-level perturbations, (4) stays hard to be detected by adversaries, and (5) converts deepfake detection and attribution into trivial tasks and outperforms the recent state-of-the-art baselines. Our solution closes the responsibility loop between publishing pre-trained generative model inventions and their possible misuses, which makes it independent of the current arms race.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Alias-Free Generative Adversarial Networks (2021, background): “Viable solutions include model watermarking [67] along with large-scale authenticity assessment in major social media sites.”
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap (2023, methodology): “For images and video, watermarking techniques can be used to combat the spread of deep fakes (e.g., Yu et al., 2021), but techniques for tracking the provenance of text are still relatively unexplored.”
AI-synthesized faces are indistinguishable from real faces and more trustworthy (2022, background): “Safeguards could include, for example, incorporating robust watermarks into the image and video synthesis networks that would provide a downstream mechanism for reliable identification (14).”
The Stable Signature: Rooting Watermarks in Latent Diffusion Models (2023, background): “In the specific case of generative models, some works deal with watemarking the training set on which the generative model is learned [98].”