Radio Identity Verification-Based IoT Security Using RF-DNA Fingerprints and SVM

It is estimated that the number of Internet-of-Things (IoT) devices will reach 75 billion in next five years. Most those currently and soon-to-be deployed lack sufficient security to protect themselves their networks from attacks by malicious IoT masquerading as authorized order circumvent digital authentication approaches. This work presents a physical (PHY) layer approach capable addressing this critical need through use feature-reduced, radio frequency-distinct native attributes (RF-DNA) fingerprints support vector machines (SVM). successfully demonstrates: 1) identity (ID) verification across three trials six randomly chosen radios at signal-to-noise ratios greater than or equal 6 dB 2) rejection all rogue ID spoofing 3 using RF-DNA whose features are selected Relief-F algorithm.