This Face Does Not Exist... But It Might Be Yours! Identity Leakage in Generative Models
By Patrick J. Tinsley, Adam Czajka, Patrick J. Flynn. 2020
46 citations recorded by the source corpus.
Generative adversarial networks (GANs) are able to generate high resolution photo-realistic images of objects that "do not exist." These synthetic images are rather difficult to detect as fake. However, the manner in which these generative models are trained hints at a potential for information leakage from the supplied training data, especially in the context of synthetic faces. This paper presents experiments suggesting that identity information in face images can flow from the training corpus into synthetic samples without any adversarial actions when building or using the existing model. This raises privacy-related questions, but also stimulates discussions of (a) the face manifold’s characteristics in the feature space and (b) how to create generative models that do not inadvertently reveal identity information of real subjects whose images were used for training. We used five different face matchers (face_recognition, FaceNet, ArcFace, SphereFace and Neurotechnology MegaMatcher) and the StyleGAN2 synthesis model, and show that this identity leakage does exist for some, but not all methods. So, can we say that these synthetically generated faces truly do not exist? Databases of real and synthetically generated faces are made available with this paper to allow full replicability of the results discussed in this work.
Subfields: Computer Vision and Pattern Recognition, Generative Models, Safety, Robustness & Interpretability
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
- Robin Rombach
- Björn Ommer
- Luc Van Gool
- Patrick Esser
- Andreas Blattmann
- Chen Change Loy
- Ming-Hsuan Yang
- Dacheng Tao
In Generative Models
- Andreas Blattmann
- Robin Rombach
- Dominik Lorenz
- Patrick Esser
- Björn Ommer
- Ying Shan
- Eric Wallace
- Borja Balle
In Safety, Robustness & Interpretability
- Florian Tramèr
- Nicholas Carlini
- Jamie Hayes
- Eric Wallace
- Matthew Jagielski
- Daphne Ippolito
- Milad Nasr
- Vikash Sehwag
Citations in the corpus
- High-Resolution Image Synthesis with Latent Diffusion Models (2021, background): “Generative models can also reveal their training data [5, 90], which is of great concern when the data contain sensitive or personal information and were collected without explicit consent.”
- Extracting Training Data from Diffusion Models (2023, background): “[70] show that StyleGAN can generate individuals’ faces, and Somepalli et al.”