Hardware changes detected using frequency and spatial fingerprinting
FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection
Machine Learning
Summary
Unauthorized changes to wireless devices can keep them looking the same but alter their physical parts, which is hard to detect. The authors present a new method that looks at device signals in terms of frequency and direction to spot these changes. Their approach uses separate ways to understand frequency details and spatial directions, then combines them to improve detection. Tests show their method works better than previous ones at finding replaced hardware parts.
What this means in practice
- •For wireless security teams: Detect hardware tampering or unauthorized replacement in wireless devices to maintain system trustworthiness.
- •For network operators: Identify physically altered devices in deployed wireless networks to prevent security breaches or malfunction.
Authors
Xiaoxuan Huang, Jinlong Xu, YiZhe Wang, Meng Zhang, Xian Li, Yuying Bian
Abstract
Unauthorized hardware replacement can preserve a wireless device's logical identity while altering its physical implementation, posing a challenge to hardware integrity verification. Spatio-frequency polarization fingerprints (SFPFs) capture device-dependent responses across multiple frequencies and directions, but their frequency and spatial dimensions exhibit different structural dependencies. We propose FreqSpaNet, an SFPF representation learning network for open set hardware anomaly detection. A frequency branch captures local variations among neighboring frequencies, while a geometry-aware spatial branch models directional relationships using angular information. The two representations are combined through adaptive fusion, and complementary pretraining further captures shared information while preserving the distinct characteristics of the frequency and spatial representations. Experiments show that FreqSpaNet achieves a mean AUROC of 96.31\%, 9.05 points above the baseline. Results under seven hardware replacement scenarios further verify the effectiveness of FreqSpaNet.