EUVIMEDOdkrijte EUVIMED
Open access · CC BY 4.0

Using JA4+ Fingerprints for Device Identification in Encrypted IoT Networks

Gemma B. Vate, Jorge E. López de Vergara, Iván González, Gustavo D. Sutter, Luis de Pedro

Electronics · 2026-11-18 · 15 (22) · 5366

DOI: 10.3390/electronics15225366 ↗

At a glance

Journal article in Electronics, published online on 2026-11-18. Written by Gemma B. Vate and 4 co-authors. 24 references. The full text is freely available (open access, CC BY 4.0). Funded by: Comunidad de Madrid.

PovzetekBibliografski podatkiCiteRelated studies

Abstract (original language)

This paper investigates whether JA4+ fingerprint decomposition improves passive identification of Internet of Things (IoT) devices in encrypted network environments, without incorporating payload inspection or active probing techniques. As TLS encryption and privacy-preserving mechanisms such as Encrypted Client Hello reduce the visibility of application-layer metadata, traditional payload- and domain-based identification techniques become less effective. JA4+ fingerprints provide an alternative approach by extracting observable characteristics from TLS handshakes, certificates, and transport-layer metadata without requiring traffic decryption. The proposed methodology evaluates different JA4+ fingerprint combinations for IoT device identification using traffic traces from the CICIoT2023 dataset, with additional validation on the UNSW-IoTraffic dataset. Traffic traces were processed with Zeek to extract the JA4+ fingerprint family, which was evaluated using dictionary-based classification, Random Forest, and Categorical Boosting models. Compact fingerprint representations were compared with decomposed protocol-level features to determine whether feature decomposition improves classification performance or enhances interpretability. Experimental results show that JA4+ fingerprints enable accurate IoT device identification using only passive encrypted traffic metadata. On CICIoT2023, the complete JA4+* configuration achieved a Macro F1-score of 0.8095 with both RF and CatBoost, although this result was obtained on a smaller subset of connections due to fingerprint availability. On the independent UNSW-IoTraffic dataset, CatBoost achieved a Macro F1-score of 0.9995 with both compact and decomposed representations. Overall, decomposed representations did not provide a consistent predictive advantage over compact fingerprints, although they remained valuable for interpretability and feature-level analysis. These findings indicate that compact JA4+ fingerprints can preserve the discriminative information required for IoT device identification without requiring protocol-level decomposition when predictive performance is the primary objective. The results highlight the potential of JA4+ fingerprinting for scalable IoT security monitoring under increasingly encrypted network conditions.

Funding

  • Comunidad de Madrid

Cite

APA

Vate, G. B., Vergara, J. E. L. D., González, I., Sutter, G. D., & Pedro, L. D. (2026). Using JA4+ Fingerprints for Device Identification in Encrypted IoT Networks. Electronics, 15(22), 5366. https://doi.org/10.3390/electronics15225366

Vancouver

Vate GB, Vergara JELD, González I, Sutter GD, Pedro LD. Using JA4+ Fingerprints for Device Identification in Encrypted IoT Networks. Electronics. 2026;15(22):5366. doi:10.3390/electronics15225366

BibTeX
@article{Vate2026,
  author = {Vate, Gemma B. and Vergara, Jorge E. López de and González, Iván and Sutter, Gustavo D. and Pedro, Luis de},
  title = {Using JA4+ Fingerprints for Device Identification in Encrypted IoT Networks},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5366},
  doi = {10.3390/electronics15225366}
}
Start for free →