Hardware Trojan Identification Using Machine Learning-based Classification

Nur Qamarina Mohd Noor, Nilam Nur Amir Sjarif, Nurul Huda Firdaus Mohd Azmi, Salwani Mohd Daud, Kamalia Kamardin

Abstract


As Hardware Trojans (HTs) emerges as the new threats for the integrated circuits (ICs), methods for identifying and detecting HTs have been widely researched and proposed. Identifying the HTs are important because it can assist in developing proper techniques for inserting and detecting the treat in ICs. One of the recent method of identifying and detecting HTs in ICs is classification using machine learning (ML) algorithm. There is still lack of machine learning-based classification for HTs identification. Thus, a three type of ML based classification includes Decision Tree (DT), K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are proposed for HTs identification. The dataset is based from the Trust-Hub. In order to improve the classification accuracy, the HTs are discretized based on their dominant attributes. The discretized HTs are classified using three machine learning algorithms. The results show that the DT and KNN learnt model are able to correctly predict about 83% of the test data.

Keywords


Classification; Hardware Trojan; Machine Learning; TrustHube;

Full Text:

PDF

References


H. Li, Q. Liu, and J. Zhang, “A survey of hardware trojan threat and defense,” Integration, the VLSI Journal, vol. 55, pp. 426-437, Sep. 2016.

H. Salmani, M. Tehranipoor, and R. Karri, “On design vulnerability analysis and trust benchmark development,” in IEEE 31st International Conference on Computer Design, 2013, pp. 471-474.

S. Moein, S. Khan, T.A Gulliver, F. Gebali, and M.W El-Kharashi, “An attribute based classification of hardware Trojans,” in IEEE 10th International Conference on Computer Engineering and System, 2015, pp. 351-356.

H. Salmani, M. Tehranipoor, and R. Karri, “On design vulnerability analysis and trust benchmark development,” in IEEE 31st International Conference on Computer Design, 2013, pp. 471-474.

N. Houghton, S. Moein, F. Gebali, and T. A. Gulliver, “An automated web tool for hardware classification,” in CSREA International Conference on Embedded Systems, Cyber-physical Systems & Applications, 2016, pp. 89-94.

M. Oya, Y. Shi, M. Yanagisawa, and N. Togawa, “A score-based classification method for identifying hardware Trojans at gate level Netlist,” in IEEE Design, Automation & Test in Europe Conference & Exhibition (DATE), 2015, pp. 465-470.

K. Hasegawa, M. Oya, M. Yanagisawa, and N. Tagawa, “Hardware Trojans classification for gate level Netlist based on machine learning,” in IEEE 22nd International Symposium on On-line testing and Robust System Design (IOLTS), 2016, pp. 203-206.

C. Bao, D. Forte, and A. Srivastava, “On application of one-class SVM to reverse engineering-based hardware Trojan detection,” in IEEE 15th International Symposium pn Quality Electronic Design, 2014, pp. 47- 54.

T. Iwase, Y. Nozaki, M. Yoshikawa, and T. Kumaki, “Detection technique for hardware Trojans using machine learning in frequency domain,” in IEEE 4th Global Conference on Consumer Electronics, 2015, pp. 185-186.

F.K Lodhi, I. Abbasi, F. Khalid, O. Hassan, F. Awwad, and S.R Hassan, “A self-learning framework to detect the intruded integrated circuits,” in IEEE International Symposium on Circuits and Systems, 2016, pp. 1702-1705.

A. Kulkarni, Y. Pino, and T. Mohsenin, “SVM-based real-time hardware Trojan detection for many-core platform,” in IEEE 17th International Symposium on Quality Electronic Design, 2016, pp. 362- 367.

A. Kulkarni, Y. Pino, and T. Mohsenin, “Trojan detection framework through machine learning,” in IEEE International Symposium on Hardware Oriented Security and Trust, 2016, pp. 120-123.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN: 2180-1843

eISSN: 2289-8131