A hardware Trojan detection method based on scan chain feature analysis

Abstract

The invention relates to a hardware Trojan detection method based on scan chain feature analysis. Starting from the gate-level netlist of an integrated circuit, a hardware Trojan detection method based on scan chain feature analysis is proposed in the chip design stage. The level netlist is first converted into a scan chain netlist, and then combined with the advantages of traditional circuit feature analysis methods, two new Trojan features are proposed, and the LightGBM algorithm is used to classify Trojan nets and normal nets. At the same time, the present invention combines the machine learning algorithm with the circuit feature analysis method and applies it in the hardware Trojan horse detection method, and has the characteristics of real-time, accurate, low-cost and the like. Aiming at the defects of high time complexity and low detection efficiency of individual Trojans in the traditional hardware Trojan circuit feature analysis method, the scanning chain netlist feature analysis method proposed by the present invention can improve the detection effect of hardware Trojans, and the machine learning LightGBM algorithm can improve the method detection efficiency.

Description

technical field [0001] The invention relates to the field of integrated circuit Trojan horse detection, in particular to a hardware Trojan horse detection method based on scan chain feature analysis. Background technique [0002] With the development of wireless communication, sensor technology, embedded system and microelectronics technology, the security of integrated circuits has received extensive attention from academia and industry in various countries. [0003] At present, hardware Trojan detection technologies can be roughly divided into two categories: formal verification and circuit feature analysis. Both methods have their own advantages and disadvantages. [0004] Formal verification is an algorithm-based logic verification method that can exhaustively prove a series of predefined security property rules that an IC design should satisfy. For example, the untrusted circuit identification technique proposed by Hicks et al. identifies suspicious circuit nets by loo...

AI Technical Summary

Problems solved by technology

This method has high detection efficiency and low cost, but the detection accuracy and efficiency of the method depend on the selection of Trojan horse features and lack of stability; Channel information is used to find hardware Trojan horses. Unfortunately, it is difficult to obtain "standard" chip samples in reality, and the detection effect of the side channel is heavily dependent on the accuracy of the instrument, which is not suitable for VLSI

Moreover, the side channel method has a weak ability to deal with the interference of process noise, and the denoising processing of bypass noise may affect the original signal again

Images