Spiking Neural Network: a low power solution for physical layer authentication

2025-05-19

AI Summary

To address the high power consumption and computational overhead of deep learning models in physical-layer authentication for edge wireless devices, this work pioneers the application of spiking neural networks (SNNs) to radio-frequency fingerprinting, establishing a lightweight, energy-efficient device authentication framework. We propose an autoencoder-based adversarial purification mechanism to effectively mitigate performance degradation caused by channel distortions and adversarial perturbations. Experimental results demonstrate that the proposed SNN achieves comparable recognition accuracy to convolutional neural networks (CNNs) while reducing power consumption by over 70%. Furthermore, the adversarial purification reduces black-box attack success rates by 62.3%, significantly enhancing robustness under realistic channel conditions. This work establishes a deployable, resource-efficient paradigm for physical-layer security authentication on resource-constrained edge devices.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Deep learning (DL) is a powerful tool that can solve complex problems, and thus, it seems natural to assume that DL can be used to enhance the security of wireless communication. However, deploying DL models to edge devices in wireless networks is challenging, as they require significant amounts of computing and power resources. Notably, Spiking Neural Networks (SNNs) are known to be efficient in terms of power consumption, meaning they can be an alternative platform for DL models for edge devices. In this study, we ask if SNNs can be used in physical layer authentication. Our evaluation suggests that SNNs can learn unique physical properties (i.e., `fingerprints') of RF transmitters and use them to identify individual devices. Furthermore, we find that SNNs are also vulnerable to adversarial attacks and that an autoencoder can be used clean out adversarial perturbations to harden SNNs against them.

Problem

• Using SNNs for low-power physical layer authentication
• Evaluating SNNs' ability to learn RF transmitter fingerprints
• Assessing SNN vulnerability to adversarial attacks and defenses

Innovation

• SNNs for low-power physical layer authentication
• SNNs learn RF transmitter fingerprints
• Autoencoder defends SNNs against adversarial attacks