Adversarial attacks have been extensively investigated for machine learning systems including deep learning in the digital domain. However, the adversarial attacks on optical neural networks (ONN) have been seldom considered previously. In this work, we first construct an accurate image classifier with an ONN using a mesh of interconnected Mach-Zehnder interferometers (MZI). Then a corresponding adversarial attack scheme is proposed for the first time. The attacked images are visually very similar to the original ones but the ONN system becomes malfunctioned and generates wrong classification results in most time. The results indicate that adversarial attack is also a significant issue for optical machine learning systems.

翻译：已经对包括数字领域深层学习在内的机器学习系统进行了广泛的反向攻击调查,然而,对光学神经网络(ONN)的对抗性攻击以前很少考虑过。在这项工作中,我们首先使用连接的Mach-Zehnder干涉仪(MZI)的网格,用ONN建立一个精确的图像分类器,并安装一个有ONN的图像分类器。然后首次提出了一个相应的对抗性攻击计划。被攻击的图像在视觉上与原始图像非常相似,但ONN系统发生故障并产生错误的分类结果。结果显示,对抗性攻击也是光学机器学习系统的一个重要问题。