IoT Device Fingerprinting From Periodic Traffic Using Locality-Sensitive Hashing

With the widespread adoption of IoT devices, their inadequate security measures make them increasingly susceptible to malicious attacks. Consequently, accurate device identification has become a critical task for safeguarding network security and privacy. This paper introduces IFPH, a novel method for IoT device fingerprinting and identification based on periodic traffic payload hashing. By exploiting the inherent periodicity in idle traffic, IFPH uses Discrete Fourier Transform (DFT) to extract the traffic's periodicity and applies Locality-Sensitive Hashing (LSH) to process packet payloads within each period. This method generates distinctive device fingerprints, facilitating efficient and reliable device identification. Unlike previous methods, IFPH addresses the inaccuracies associated with fixed-time window fingerprinting and eliminates the need for complex feature extraction or model training. Experimental results reveal that IFPH surpasses existing techniques, achieving accuracy and recall rates exceeding 95% on publicly available datasets.