Adversarial attacks on an optical neural network

Autor:	Jiao, Shuming, Song, Ziwei, Xiang, Shuiying
Rok vydání:	2022
Předmět:	Computer Science - Cryptography and Security Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2205.01226 Zobrazit plný text záznamu View this record from Arxiv