SFPF: Spatio-Frequency Polarization Fingerprint for Anomalous Wireless Device Detection
SFPF fingerprinting detects swapped wireless hardware better than RF or single-direction polarization fingerprints.
The paper proposes a spatio-frequency polarization fingerprint (SFPF) to detect unauthorized replacement of wireless devices when communication, credentials, and logical identity stay unchanged. SFPF jointly captures complex polarization responses across frequencies and observation directions. Simulations improve normalized distance, Fisher score, and inter-/intra-class ratio over single-direction polarization fingerprints by 17.7%, 45.8%, and 11.3%. At 15–20 dB SNR, anomalous-device F1 is 87.3–90.4% and AUROC is 85.4–95.5%.
- Detects unauthorized radio hardware that keeps credentials and logical identity.
- Combines polarization responses over frequencies and viewing directions.
- Beats single-direction fingerprints by 17.7%, 45.8%, and 11.3% on three metrics.
- At 15–20 dB, F1 is 87.3–90.4% and AUROC is 85.4–95.5%.
From the original article
1 min read at arxiv.orgPeriodic inspection of deployed wireless devices is necessary because unauthorized hardware replacement may preserve communication functions, credentials, and logical identity, making anomalous devices difficult to detect. Such inspections are conducted under controlled measurement conditions to verify that each device remains consistent with its enrolled hardware state.
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.