Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method

Abstract

Intelligent Internet of Things (IoT) systems based on deep neural networks (DNNs) have been widely deployed in the real world. However, DNNs are found to be vulnerable to adversarial examples, which raises people's concerns about intelligent IoT systems' reliability and security. Testing and evaluating the robustness of IoT systems becomes necessary and essential. Recently various attacks and strategies have been proposed, but the efficiency problem remains unsolved properly. Existing methods are either computationally extensive or time-consuming, which is not applicable in practice. In this paper, we propose a novel framework called Attack-Inspired GAN (AI-GAN) to generate adversarial examples conditionally. Once trained, it can generate adversarial perturbations efficiently given input images and target classes. We apply AI-GAN on different datasets in white-box settings, black-box settings and targeted models protected by state-of-the-art defenses. Through extensive experiments, AI-GAN achieves high attack success rates, outperforming existing methods, and reduces generation time significantly. Moreover, for the first time, AI-GAN successfully scales to complex datasets e.g. CIFAR-100 and ImageNet, with about $90\%$ success rates among all classes.

arXiv admin note: text overlap with arXiv:2002.02196

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Explaining and Harnessing Adversarial Examples
• A Simple Framework for Contrastive Learning of Visual Representations
• Intriguing properties of neural networks
• Ensemble Adversarial Training: Attacks and Defenses
• Generative Adversarial Text to Image Synthesis
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Unified Language Model Pre-training for Natural Language Understanding and Generation
• Wasserstein GAN
• Massively Multitask Networks for Drug Discovery
• cGANs with Projection Discriminator
• Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• Constructing Unrestricted Adversarial Examples with Generative Models
• GAP++: Learning to generate target-conditioned adversarial examples