Zero-Bias Deep Learning for Accurate Identification of Internet-of-Things (IoT) Devices

The Internet of Things (IoT) provides applications and services that would otherwise not be possible. However, the open nature IoT makes it vulnerable to cybersecurity threats. Especially, identity spoofing attacks, where an adversary passively listens existing radio communications then mimic legitimate devices conduct malicious activities. Existing solutions employ cryptographic signatures verify trustworthiness received information. In prevalent IoT, secret keys for cryptography can potentially disclosed disable verification mechanism. Noncryptographic device is needed ensure trustworthy IoT. this article, we propose enhanced deep learning framework identification using physical-layer signals. Specifically, enable our report unseen introduce zero-bias layer neural networks increase robustness interpretability. We have evaluated effectiveness proposed real data from automatic dependent surveillance-broadcast (ADS-B), application in aviation. has potential applied accurate a variety services.