Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers

arXiv:2404.11665v1 Announce Type: new
Abstract: Deep Neural Networks (DNNs) have advanced in many real-world applications, such as healthcare and autonomous driving. However, their high computational complexity and vulnerability to adversarial attacks are ongoing challenges. In this letter, approximate multipliers are used to explore DNN robustness improvement against adversarial attacks. By uniformly replacing accurate multipliers for state-of-the-art approximate ones in DNN layer models, we explore the DNNs robustness against various adversarial attacks in a feasible time. Results show up to 7% …

abstract advanced adversarial adversarial attacks applications arxiv attacks autonomous autonomous driving challenges complexity computational cs.cr cs.lg dnn driving explore healthcare however improvement networks neural networks robustness type vulnerability world