Spiking Neural Network: a low power solution for physical layer authentication
This work addresses power efficiency for edge device security in wireless networks, but it is incremental as it adapts existing SNN methods to a new application domain.
The study tackled the problem of deploying deep learning for physical layer authentication on resource-constrained edge devices by proposing Spiking Neural Networks (SNNs) as a low-power alternative, showing they can learn unique RF transmitter fingerprints to identify devices but are also vulnerable to adversarial attacks, which can be mitigated using an autoencoder.
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.