Physics‐Aware Machine Learning and Adversarial Attack in Complex‐Valued Reconfigurable Diffractive All‐Optical Neural Network. Issue 12 (15th August 2022)

• Record Type: Journal Article
• Authors: Chen, Ruiyang; Li, Yingjie; Lou, Minhan; Fan, Jichao; Tang, Yingheng; Sensale‐Rodriguez, Berardi; Yu, Cunxi; Gao, Weilu
• Is Part Of: Laser & photonics reviews. Volume 16:Issue 12(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-08-15
• Subjects: adversarial attacks -- machine learning -- physics‐aware training -- reconfigurable diffractive all‐optical neural networks; Lasers -- Periodicals; Photonics -- Periodicals; Lasers -- Périodiques; Photonique -- Périodiques; 621.36
• DOI: 10.1002/lpor.202200348
• Languages: English
• ISSNs: 1863-8880

Abstract

Abstract: Diffractive optical neural networks have shown promising advantages over electronic circuits for accelerating modern machine learning (ML) algorithms. However, it is challenging to achieve fully programmable all‐optical implementation and rapid hardware deployment. Here, a large‐scale, cost‐effective, complex‐valued, and reconfigurable diffractive all‐optical neural networks system in the visible range is demonstrated based on cascaded transmissive twisted nematic liquid crystal spatial light modulators. The employment of categorical reparameterization technique creates a physics‐aware training framework for the fast and accurate deployment of computer‐trained models onto optical hardware. Such a full stack of hardware and software enables not only the experimental demonstration of classifying handwritten digits in standard datasets, but also theoretical analysis and experimental verification of physics‐aware adversarial attacks onto the system, which are generated from a complex‐valued gradient‐based algorithm. The detailed adversarial robustness comparison with conventional multiple layer perceptrons and convolutional neural networks features a distinct statistical adversarial property in diffractive optical neural networks. The developed full stack of software and hardware provides new opportunities of employing diffractive optics in a variety of ML tasks and in the research on optical adversarial ML. Abstract : A full stack of complex‐valued reconfigurable diffractive all‐optical neural networks hardware and associated physics‐aware training software for fast and accurate deployment is demonstrated. Such a full stack of hardware and software enables not only the classification of standard handwritten digits, but also the exploration of an uncharted area of adversarial attacks in complex‐valued neural networks.