# Adversarial attacks on an optical neural network

arXiv: https://arxiv.org/abs/2205.01226 · HTML: https://mlsanity.com/paper/2205.01226/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 29 Apr 2022.

## Builds on (most cited first, 13 of 13)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Dive into Deep Learning](https://mlsanity.com/paper/2106.11342/) (2021)
- [Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer](https://mlsanity.com/paper/2203.03121/) (2022)
- [Training of photonic neural networks through in situ backpropagation](https://mlsanity.com/paper/1805.09943/) (2018)
- [Optical Adversarial Attack](https://mlsanity.com/paper/2108.06247/) (2021)
- [Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks](https://mlsanity.com/paper/1810.01916/) (2018)
- [A black-box adversarial attack for poisoning clustering](https://mlsanity.com/paper/2009.05474/) (2020)
- [Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack](https://mlsanity.com/paper/2103.03438/) (2021)
- [Optical machine learning with incoherent light and a single-pixel detector](https://mlsanity.com/paper/1904.10851/) (2019)
- [Efficient training and design of photonic neural network through neuroevolution](https://mlsanity.com/paper/1908.08012/) (2019)

## Abstract (arXiv)

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.