SecONN: An Optical Neural Network Framework with Concurrent Detection of Thermal Fault Injection Attacks

Autor:	Nishida, Kota, Midoh, Yoshihiro, Miura, Noriyuki, Kawakami, Satoshi, Shiomi, Jun
Rok vydání:	2024
Předmět:	Physics - Optics Computer Science - Cryptography and Security
Druh dokumentu:	Working Paper
Popis:	Silicon Photonics-based AI Accelerators (SPAAs) have been considered as promising AI accelerators achieving high energy efficiency and low latency. While many researchers focus on improving SPAAs' energy efficiency and latency, their physical security has not been sufficiently studied. This paper first proposes a threat of thermal fault injection attacks on SPAAs based on Vector-Matrix Multipliers (VMMs) utilizing Mach-Zhender Interferometers. This paper then proposes SecONN, an optical neural network framework that is capable of not only inferences but also concurrent detection of the attacks. In addition, this paper introduces a concept of Wavelength Division Perturbation (WDP) where wavelength dependent VMM results are utilized to increase detection accuracy. Simulation results show that the proposed method achieves 88.7% attack-caused average misprediction recall.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.14741 Zobrazit plný text záznamu View this record from Arxiv