Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers
Machine Learning
2024-04-19 v1 Cryptography and Security
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% accuracy drop due to approximations when no attack is present while improving robust accuracy up to 10% when attacks applied.
Cite
@article{arxiv.2404.11665,
title = {Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers},
author = {Mohammad Javad Askarizadeh and Ebrahim Farahmand and Jorge Castro-Godinez and Ali Mahani and Laura Cabrera-Quiros and Carlos Salazar-Garcia},
journal= {arXiv preprint arXiv:2404.11665},
year = {2024}
}