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.

翻译：深度神经网络已在医疗保健和自动驾驶等众多实际应用中取得进展。然而，其高计算复杂度与易受对抗攻击的脆弱性仍是持续存在的挑战。本文采用近似乘法器，探究深度神经网络在对抗攻击下的鲁棒性提升方法。通过将DNN层模型中的精确乘法器统一替换为最先进的近似乘法器，我们在可行时间内探究了DNNs对各种对抗攻击的鲁棒性。结果表明：无攻击时，近似操作导致准确率下降最高达7%；而在施加攻击时，鲁棒准确率提升最高可达10%。