EM Side-Channel Based Trojan Detection Using Deep SVDD For Unsupervised Anomaly Identification

Article Sidebar

PDF
Published: Sep 23, 2026
DOI: https://doi.org/10.66669/cineforum.v66iS6.1620
Keywords:
Electromagnetic side channel; hardware Trojan; Deep SVDD; one-class classification; FFT; anomaly detection; Verilog.

Main Article Content

Yasala Charishma Raghavi
L. Chandra Shekhar
Miriampally Venkata Raghavendra

Abstract

Integrated-circuit design and fabrication worldwide have brought about greater chances of malicious manipulation of hardware functionalities that might not be detected through standard functional test. In this paper, an electromagnetic (EM) side-channel platform on Deep Support Vector Data Description (Deep SVDD) is used to detect hardware- Trojan. The technique measures the non-invasive EM emissions of a test device, conditions and digitalizes the signal, and processes the signal with Hann windowing and Fast Fourier Transformer analysis, and calculates the magnitude-squared spectrum. Strong sibling spectral peaks around the location of operating-clocks are picked up in order to create a small feature-vector. Deep SVDD uses exclusively golden, Trojan-free features with which it learns a concise latent-space representation of the normal behaviour. Online functionality When a new feature vector is mapped with the trained model their squared distance to the learned centre is contrasted against the threshold to yield a normal-or-Trojan decision. MATLAB facilitates the preparation of data and offline training of a model, whereas the hardware-oriented processing chain is modelled using the Verilog modules of FFT interfacing, power-spectrum generation, peak extraction, anomaly scoring, and top-level detection. The architecture is not reliant on labelled Trojan samples, and allows the detection of new structural changes that were never seen before. The feasibility of implementation, functional validation requirements, constraint and directions of quantitative FPGA and ASIC benchmarking are also discussed.

Article Details

How to Cite
Raghavi, Y. C., Shekhar, L. C., & Raghavendra, M. V. (2026). EM Side-Channel Based Trojan Detection Using Deep SVDD For Unsupervised Anomaly Identification. CINEFORUM, 66(S6), 417–430. https://doi.org/10.66669/cineforum.v66iS6.1620
Issue
Vol. 66 No. S6 (2026)
Section
Original Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

References

M. Tehranipoor and F. Koushanfar, “A survey of hardware Trojan taxonomy and detection,” IEEE Design Test Comput., vol. 27, no. 1, pp. 10–25, 2010.

R. Karri, J. Rajendran, K. Rosenfeld, and M. Tehranipoor, “Trustworthy hardware: Identifying and classifying hardware Trojans,” Computer, vol. 43, no. 10, pp. 39–46, 2010.

R. S. Chakraborty, S. Narasimhan, and S. Bhunia, “Hardware Trojan: Threats and emerging solutions,” in Proc. IEEE High-Level Design Validation Test Workshop (HLDVT), 2009, pp. 166–171.

S. Narasimhan, X. Wang, D. Du, R. S. Chakraborty, and S. Bhunia, “Multiple-parameter side-channel analysis for hardware Trojan detection,” IEEE Trans. Comput., vol. 62, no. 11, pp. 2183–2195, 2013.

J. Rajendran, O. Sinanoglu, and R. Karri, “Security analysis of logic obfuscation,” in Proc. Design Autom. Conf. (DAC), 2012, pp. 83–89.

Y. Jin and Y. Makris, “Hardware Trojan detection using path delay fingerprint,” in Proc. IEEE Int. Symp. Hardware-Oriented Security Trust (HOST), 2008, pp. 51–57.

J. He, Y. Zhao, X. Guo, and Y. Jin, “Hardware Trojan detection through electromagnetic side-channel analysis,” IEEE Trans. Very Large Scale Integr. (VLSI) Syst., vol. 25, no. 10, pp. 2939–2948, 2017.

Y. Zheng, S. Bhunia, and S. Yang, “Self-referencing-based Trojan detection without a golden chip,” IEEE Trans. Comput.-Aided Design Integr. Circuits Syst., vol. 35, no. 1, pp. 37–48, 2016.

B. Schölkopf et al., “Support vector method for novelty detection,” in Advances in Neural Information Processing Systems, 1999.

L. Ruff et al., “Deep one-class classification,” in Proc. Int. Conf. Mach. Learn. (ICML), 2018, pp. 4393–4402.

M. A. Kramer, “Autoassociative neural networks,” Comput. Chem. Eng., vol. 16, no. 4, pp. 313–328, 1992.

D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, pp. 533–536, 1986.

S. Sankaran et al., “Deep learning-based approach for hardware Trojan detection,” in Proc. IEEE Int. Symp. Smart Electronic Systems (iSES), 2021.

K. G. Liakos et al., “Machine learning for hardware Trojan detection: A review,” in Proc. PACET, 2019.

Z. Huang et al., “A survey on machine learning against hardware Trojan attacks,” IEEE Access, vol. 8, pp. 10796–10826, 2020.

A. Sumarsono and Z. Masters, “Application of LSTM autoencoder in Trojan detection,” in Proc. IEEE Comput. Commun. Workshop Conf. (CCWC), 2023.

S. Faezi, R. Yasaei, and M. A. Al Faruque, “HTNet: Transfer learning for Trojan detection,” in Proc. Design, Autom. Test Eur. Conf. Exhib. (DATE), 2021.

J. Takahashi et al., “Machine learning-based Trojan detection using electromagnetic emanation,” IEICE Trans., 2022.

L. N. Nguyen et al., “Backscattering side-channel for Trojan detection,” IEEE Trans. Very Large Scale Integr. (VLSI) Syst., vol. 27, no. 7, pp. 1561–1574, 2019.

H. Li, Q. Liu, and J. Zhang, “A survey of hardware Trojan threat and defense,” Integration, vol. 55, pp. 426–437, 2016.

J. He et al., “Golden chip-free Trojan detection leveraging electromagnetic fingerprinting,” IEICE Electron. Express, 2019.

K. Xiao et al., “Hardware Trojans: Lessons learned after one decade of research,” ACM Trans. Design Autom. Electron. Syst., vol. 22, no. 1, 2016.

S. Wang et al., “Trojan detection based on an extreme learning machine neural network,” in Proc. Int. Conf. Comput. Commun. Informatics (ICCCI), 2016.

M. Priyatharishini and M. N. Devi, “Deep learning-based malicious module identification,” Measurement, vol. 194, 2022.

N. Nour et al., “Machine learning-based Trojan identification,” J. Telecommun., 2017.

L. Zhang et al., “Trojan detection using electromagnetic leakage,” China Commun., vol. 16, no. 12, pp. 100–110, 2019.

A. Fournaris et al., “FPGA Trojan detection using multiple parameters,” Microprocess. Microsyst., 2019.

J. U. Ko et al., “Autoencoder-based anomaly detection with a dynamic threshold,” Expert Syst. Appl., 2022.

P. Bergmann et al., “Unsupervised defect detection using autoencoders,” arXiv preprint arXiv:1807.02011, 2018.

F. Wan et al., “Outlier detection using a stacked autoencoder,” IEEE Access, vol. 7, 2019