A Self-learning Framework to Detect the Intruded Integrated Circuits

Faiq Khalid Lodhi , Imran Hafeez Abbasi, Faiz Khalid Lodhi, Osman Hasan Falah Awwadand Syed Rafay Hasan

Abstract

Globalization trends in integrated circuit (IC) design using deep submicron (DSM) technologies are leading to increased vulnerability of ICs against malicious intrusions. These malicious intrusions are referred as hardware Trojans. One way to address this threat is to utilize unique electrical signatures of ICs. However, these techniques require analysis of extensive sensor data to detect the intruded integrated circuits. Therefore, in this paper we combine the signature extraction mechanism with machine learning algorithms to develop a self–learning framework that can detect the intruded integrated circuits. The proposed approach applies the lazy, eager or probabilistic learners to generate self-learning prediction model based on the electrical signatures. In order to validate this framework, we applied most commonly used lazy, eager and probabilistic learners on a recently proposed signature based hardware trojan detection technique. The cross validation comparison of these learner shows that eager learners are able to detect the intrusion with 96% accuracy and also require less amount of memory and processing power compared to other machine learning techniques.

nad

Proposed Framework to Identify Intruded Integrated Circuits

nad

Effect of Process and Mismatch Variation on Delay

nad

Data Transformation (Numeric to Nominal) Rules

nad

Performance Comparison (DT, BC AND KNN)

nad

Decision Tree

Publications

  1. F. K. Lodhi, I. Abbasi, F. Khalid, O. Hasan, S. R. Hasan and F. Awwad,”A Self-Learning Framework to Detect the Intruded Integrated Circuits“, in IEEE Symposium on circuits and System (ISCAS 2016), Montreal, Canada, To Appear.