Hardware Fingerprint Authentication Based on Siamese Neural Networks in PON

This letter presents a novel approach to bolster the physical layer security of optical communication systems, specifically within Passive Optical Networks (PONs), through the utilization of device fingerprints. In this proposed scheme, we employ Optical On-Off Keying (OOK) modulation for signal transmission and subsequently extract distinct fingerprint features from the eye diagrams of these OOK signals. These fingerprint features are then subjected to dimensionality reduction via Siamese neural networks. Subsequently, a set of classifiers is utilized to discriminate among the downscaled feature data, thereby achieving robust authentication for up to 10 ONUs in a 20 km Single-Mode Fiber (SSMF) transmission. Remarkably, the recognition accuracy attained in our experiments reached 96.04%. Moreover, this system exhibits the capacity for transfer learning of fingerprint features when new devices are introduced into the network. This feature speeds up the authentication of new devices coming online.

I. Introduction

With the continuous development of optical communication, the security of optical network is receiving more and more attention. A variety of attacks such as eavesdropping, interception and identity spoofing occur in the physical layer of optical networks, so physical layer security is of increasing concern. In order to maintain the security of the physical layer, researchers have come up with many solutions from different directions. The security of traditional public key-based cryptographic schemes derives mainly from the complexity of the algorithm [1]. Other schemes include unclonable functions using challenge-response mechanisms [2], secret key distribution based on channel characteristics [3], etc. In recent years, there has been an increase in research into chaotic encryption, which is the use of the characteristics of chaotic signals to achieve encryption [4], [5]. With the introduction of QNSC, high-speed and long-range secure communication solutions based on QNSC were also proposed [6].