Detecting Hardware Trojans in Cryptography Devices Using Machine Learning
https://doi.org/10.35596/1729-7648-2025-23-6-71-79
Abstract
The current technological race to increase the volume of received, processed, and transmitted information plays a crucial role in the security of any country, as these areas are fundamental for the deployment of complex linguistic and experimental models, or frontier models, used in digital ecosystems and military affairs. This is particularly true for communications equipment and the strength of their cryptographic encryption. Compromising transmitted information, hidden from official subscribers of a closed radio network, can cause far greater damage than its failure. Given the rapid pace of change and innovation, countries without their own manufacturing capabilities are forced to manufacture digital encryption modules in other countries, which carries the risk of introducing hardware Trojans. This article describes the results of software testing of a neural network capable of detecting information compromise in an AES-256 (Advanced Encryption Standard) encryption module based on the analysis of received and transmitted information without a “golden reference”.
About the Authors
A. Yu. Voronov
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Voronov Aleksey Yuryevich, Postgraduade of the Department of Micro- and Nanoelectronics
220013, Minsk, P. Brovki St., 6
Tel.: +375 29 353-52-74
V. R. Stempitsky
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Cand. Sci. (Tech.), Associate Professor, Vice-Rector for Academic Affairs, Advicer of the R&D Laboratory “Computer-Aided Design of Micro- and Nanoelectronic Systems”
220013, Minsk, P. Brovki St., 6
Tel.: +375 29 353-52-74
References
1. Tehranipoor M., Koushanfar F. (2010) A Survey of Hardware Trojan Taxonomy and Detection. IEEE Design & Test of Computers. 27 (1), 10–25. DOI: 10.1109/MDT.2010.
2. Chen Z. (2020) Deep Learning for Cybersecurity: A Review. 2020 International Conference on Computing and Data Science (CDS), Stanford, CA, USA. 7–18. DOI: 10.1109/CDS49703.2020.00009.
3. Yasaei R., Chen L., Yu S.-Y., Al Faruque M. A. (2025) Hardware Trojan Detection Using Graph Neural Networks. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst. 44 (1), 25–38.
4. Ashok M., Turner M. J., Walsworth R. L., Levine E. V., Chandrakasan A. P. (2022). Hardware Trojan Detection Using Unsupervised Deep Learning on Quantum Diamond Microscope Magnetic Field Images. ACM Journal on Emerging Technologies in Computing Systems. 18 (4), 1–25.
5. Xilinx Power Estimator User Guide (UG440). Santa Clara, California: AMD/ Xilinx, 2023.
6. Vivado Design Suite User Guide (UG901). Santa Clara, California: AMD/ Xilinx, 2020.
7. Tarasov I. E. (2021) Xilinx FPGAs. VHDL and Verilog Hardware Description Languages, CAD, and Design Techniques. Moscow, Goryachaya Liniya – Telekom Publ. (in Russian).
8. Belous A. I., Soloduha V. A., Shvedov S. V. (2019) Software and Hardware Trojans – Methods of Deployment and Countermeasures. The First Technical Encyclopedia in Two Books. Moscow, Technosphera Publ. (in Russian).
Review
For citations:
Voronov A.Yu., Stempitsky V.R. Detecting Hardware Trojans in Cryptography Devices Using Machine Learning. Doklady BGUIR. 2025;23(6):71-79. (In Russ.) https://doi.org/10.35596/1729-7648-2025-23-6-71-79
Views:
27
Email this article 