Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
This addresses the efficiency bottleneck in testing IoT system security, though it is incremental as it builds on existing adversarial attack methods.
The paper tackles the problem of efficiently evaluating the robustness of deep neural networks in IoT systems by proposing a GAN-based method called AI-GAN, which generates adversarial examples with high success rates (e.g., about 90% on complex datasets) and significantly reduces generation time.
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.