mlsanityData to 14 Oct 2026

Adversarial attacks on an optical neural network

arXiv 2205.01226 ↗First posted 29 Apr 2022cs.CR cs.CV cs.LGcited by 0

Not on the map. Why?

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.

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

13 of 34 references.

References · 13

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  4. 2018All-Optical Machine Learning Using Diffractive Deep Neural Networkscited by 177
  5. 2021Dive into Deep Learningcited by 111
  6. 2022Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfercited by 78
  7. 2018Training of photonic neural networks through in situ backpropagationcited by 45
  8. 2021Optical Adversarial Attackcited by 43
  9. 2018Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networkscited by 30
  10. 2020A black-box adversarial attack for poisoning clusteringcited by 16
  11. 2021Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attackcited by 15
  12. 2019Optical machine learning with incoherent light and a single-pixel detectorcited by 8
1 more
  1. 2019Efficient training and design of photonic neural network through neuroevolutioncited by 7

Built on by

Not cited yet.