# SafeLight: Enhancing Security in Optical Convolutional Neural Network Accelerators

arXiv: https://arxiv.org/abs/2411.16712 · HTML: https://mlsanity.com/paper/2411.16712/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 22 Nov 2024.

## Builds on (most cited first, 14 of 14)

- [TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings](https://mlsanity.com/paper/2304.01433/) (2023)
- [Deep Defense: Training DNNs with Improved Adversarial Robustness](https://mlsanity.com/paper/1803.00404/) (2018)
- [CrossLight: A Cross-Layer Optimized Silicon Photonic Neural Network Accelerator](https://mlsanity.com/paper/2102.06960/) (2021)
- [ROBIN: A Robust Optical Binary Neural Network Accelerator](https://mlsanity.com/paper/2107.05530/) (2021)
- [Hardware Trojan Attacks on Neural Networks](https://mlsanity.com/paper/1806.05768/) (2018)
- [RecLight: A Recurrent Neural Network Accelerator with Integrated Silicon Photonics](https://mlsanity.com/paper/2209.00084/) (2022)
- [TRON: Transformer Neural Network Acceleration with Non-Coherent Silicon Photonics](https://mlsanity.com/paper/2303.12914/) (2023)
- [SONIC: A Sparse Neural Network Inference Accelerator with Silicon Photonics for Energy-Efficient Deep Learning](https://mlsanity.com/paper/2109.04459/) (2021)
- [A Silicon Photonic Accelerator for Convolutional Neural Networks with Heterogeneous Quantization](https://mlsanity.com/paper/2205.11244/) (2022)
- [Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks](https://mlsanity.com/paper/1805.05098/) (2018)
- [GHOST: A Graph Neural Network Accelerator using Silicon Photonics](https://mlsanity.com/paper/2307.01782/) (2023)
- [Cross-Layer Design for AI Acceleration with Non-Coherent Optical Computing](https://mlsanity.com/paper/2303.12910/) (2023)
- [Accelerating Neural Networks for Large Language Models and Graph Processing with Silicon Photonics](https://mlsanity.com/paper/2401.06885/) (2024)
- [Silicon Photonic 2.5D Interposer Networks for Overcoming Communication Bottlenecks in Scale-out Machine Learning Hardware Accelerators](https://mlsanity.com/paper/2403.04189/) (2024)

## Built on by (most cited first, 4 of 4)

- [PhotoGAN: Generative Adversarial Neural Network Acceleration with Silicon Photonics](https://mlsanity.com/paper/2501.13828/) (2025)
- [Accelerating Diffusion Models for Generative AI Applications with Silicon Photonics](https://mlsanity.com/paper/2603.07626/) (2026)
- [Sustainable Transformer Neural Network Acceleration with Stochastic Photonic Computing](https://mlsanity.com/paper/2604.09759/) (2026)
- [Hardware Trojan Threats to Multi-Chiplet Photonic Neural Network Accelerators](https://mlsanity.com/paper/2609.06796/) (2026)

## Abstract (arXiv)

The rapid proliferation of deep learning has revolutionized computing hardware, driving innovations to improve computationally expensive multiply-and-accumulate operations in deep neural networks. Among these innovations are integrated silicon-photonic systems that have emerged as energy-efficient platforms capable of achieving light speed computation and communication, positioning optical neural network (ONN) platforms as a transformative technology for accelerating deep learning models such as convolutional neural networks (CNNs). However, the increasing complexity of optical hardware introduces new vulnerabilities, notably the risk of hardware trojan (HT) attacks. Despite the growing interest in ONN platforms, little attention has been given to how HT-induced threats can compromise performance and security. This paper presents an in-depth analysis of the impact of such attacks on the performance of CNN models accelerated by ONN accelerators. Specifically, we show how HTs can compromise microring resonators (MRs) in a state-of-the-art non-coherent ONN accelerator and reduce classification accuracy across CNN models by up to 7.49% to 80.46% by just targeting 10% of MRs. We then propose techniques to enhance ONN accelerator robustness against these attacks and show how the best techniques can effectively recover the accuracy drops.