This Face Does Not Exist... But It Might Be Yours! Identity Leakage in Generative Models

  title={This Face Does Not Exist... But It Might Be Yours! Identity Leakage in Generative Models},
  author={Patrick J. Tinsley and Adam Czajka and Patrick J. Flynn},
  journal={2021 IEEE Winter Conference on Applications of Computer Vision (WACV)},
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… 

Figures and Tables from this paper

Fooling a Face Recognition System with a Marker-Free Label-Consistent Backdoor Attack

This paper generates a label-consistent poisoned dataset, where the poisoned images matches their labels and are di cult to spot by a quick visual inspection, and shows that the network finetuned on the poisoned dataset is successfully fooled, identifying one of the author as a specific target identity.

Analyzing the Impact of Shape & Context on the Face Recognition Performance of Deep Networks

—In this article, we analyze how changing the un- derlying 3D shape of the base identity in face images can distort their overall appearance, especially from the perspective of deep face recognition.

PrintsGAN: Synthetic Fingerprint Generator.

This work proposes PrintsGAN, a synthetic fingerprint generator capable of generating unique fingerprints along with multiple impressions for a given fingerprint, and synthesizes a database of 525 k fingerprints, which is released to the public.

When do GANs replicate? On the choice of dataset size

It is shown that dataset size and its complexity play an important role in GANs replication and perceptual quality of the generated images and a practical tool for one-shot estimation on minimal dataset size is found which can be used to guide datasets construction and selection.

Synthetic Data in Human Analysis: A Survey

A novel UDA approach for action recogni- tion from videos, inspired by recent literature on contrastive learning is introduced, and a novel two-headed deep architecture that simultaneously adopts cross-entropy and contrastive losses from different net- work branches to robustly learn a target classifier is proposed.

High-Resolution Image Synthesis with Latent Diffusion Models

These latent diffusion models achieve new state-of-the-art scores for image inpainting and class-conditional image synthesis and highly competitive performance on various tasks, includ-ing text-to-image synthesis, unconditional image generation and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

Biometrics: Trust, But Verify

Insightful insights are provided into how the biometric community can address core biometric recognition systems design issues to better instill trust, fairness, and security for all.

GAUDI: A Neural Architect for Immersive 3D Scene Generation

GAUDI obtains state-of-the-art performance in the unconditional generative setting across multiple datasets and allows for conditional generation of 3D scenes given conditioning variables like sparse image observations or text that describes the scene.



GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection

The results obtained in the empirical evaluation show that additional efforts are required to develop robust facial manipulation detection systems against unseen conditions and spoof techniques, such as the one proposed in this study.

DeepFakes: a New Threat to Face Recognition? Assessment and Detection

This paper presents the first publicly available set of Deepfake videos generated from videos of VidTIMIT database, and demonstrates that GAN-generated Deep fake videos are challenging for both face recognition systems and existing detection methods.

Differentially Private Data Generative Models

It is demonstrated that both DP-AuGM and DP-VaeGM can be easily integrated with real-world machine learning applications, such as machine learning as a service and federated learning, which are otherwise threatened by the membership inference attack and the GAN-based attack, respectively.

A Style-Based Generator Architecture for Generative Adversarial Networks

An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.

VGGFace2: A Dataset for Recognising Faces across Pose and Age

A new large-scale face dataset named VGGFace2 is introduced, which contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject, and the automated and manual filtering stages to ensure a high accuracy for the images of each identity are described.

GANobfuscator: Mitigating Information Leakage Under GAN via Differential Privacy

GANobfuscator, a differentially private GAN, which can achieve differential privacy under GANs by adding carefully designed noise to gradients during the learning procedure, is proposed and theoretically proves that GANob obfuscator can provide strict privacy guarantee with differential privacy.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a

SphereFace: Deep Hypersphere Embedding for Face Recognition

This paper proposes the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features in deep face recognition (FR) problem under open-set protocol.

Analyzing and Improving the Image Quality of StyleGAN

This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.