FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection
FreqSpaNet learns spatio-frequency polarization fingerprints to detect unauthorized wireless hardware replacement, reaching 96.31% mean AUROC across seven replacement scenarios.
FreqSpaNet is a representation learning network for open-set hardware anomaly detection using spatio-frequency polarization fingerprints (SFPFs), which capture device-dependent responses across frequencies and directions. A frequency branch models local variations among neighboring frequencies while a geometry-aware spatial branch models directional relationships via angular information, combined through adaptive fusion and complementary pretraining. It achieves a mean AUROC of 96.31%, 9.05 points above the baseline, and is verified under seven hardware replacement scenarios.
- Detects unauthorized hardware replacement that preserves logical device identity
- Frequency branch plus geometry-aware spatial branch with adaptive fusion
- 96.31% mean AUROC, 9.05 points above baseline
- Validated across seven hardware replacement scenarios
From the original article
1 min read at arxiv.orgUnauthorized 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.
By Xiaoxuan Huang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.