Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network

Abstract

With the broad use of face recognition, its weakness gradually emerges that it is able to be attacked. So, it is important to study how face recognition networks are subject to attacks. In this paper, we focus on a novel way to do attacks against face recognition network that misleads the network to identify someone as the target person not misclassify inconspicuously. Simultaneously, for this purpose, we introduce a specific attentional adversarial attack generative network to generate fake face images. For capturing the semantic information of the target person, this work adds a conditional variational autoencoder and attention modules to learn the instance-level correspondences between faces. Unlike traditional two-player GAN, this work introduces face recognition networks as the third player to participate in the competition between generator and discriminator which allows the attacker to impersonate the target person better. The generated faces which are hard to arouse the notice of onlookers can evade recognition by state-of-the-art networks and most of them are recognized as the target person.

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Explaining and Harnessing Adversarial Examples
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Learning Face Representation from Scratch
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• DeepID3: Face Recognition with Very Deep Neural Networks
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Distributional Smoothing with Virtual Adversarial Training
• Learning with a Strong Adversary
• Disentangling factors of variation in deep representations using adversarial training
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Non-local Neural Networks
• Web-Scale Training for Face Identification
• Geometric robustness of deep networks: analysis and improvement

Cited by in corpus (8)

• Detection of Face Recognition Adversarial Attacks
• Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition
• Adaptive Generation of Unrestricted Adversarial Inputs
• Adversarial Learning with Margin-based Triplet Embedding Regularization
• Measurement-driven Security Analysis of Imperceptible Impersonation Attacks
• Dodging Attack Using Carefully Crafted Natural Makeup
• Robust Attacks on Deep Learning Face Recognition in the Physical World
• Amora: Black-box Adversarial Morphing Attack