Hardware Trojan horse detection method based on LUT feature extraction and machine learning

Abstract

The invention discloses a hardware Trojan horse detection method based on LUT feature extraction and machine learning. The hardware Trojan horse detection method comprises the following steps: inputting an integrated circuit design embedded with a hardware Trojan horse as a training set; designing and synthesizing the training integrated circuit into a field programmable gate array netlist; hardware Trojan horse feature extraction is carried out on the FPGA netlist, and generated training quantization feature values are stored; training a machine learning classifier by using the training quantization feature value to generate an optimal hardware Trojan classifier; inputting a to-be-detected integrated circuit design; designing and synthesizing a to-be-detected integrated circuit into a to-be-detected FPGA netlist; hardware Trojan horse feature extraction is carried out on the FPGA netlist to be measured, and generated feature values to be measured are stored; and inputting a to-be-measured characteristic value into the trained hardware Trojan classifier, and dividing the to-be-detected integrated circuit into Trojan nodes and normal nodes, thereby realizing Trojan detection. According to the method, hardware Trojan horse detection activated based on specific conditions can be realized, and hardware Trojan horse potential safety hazards can be detected in the early stage of integrated circuit design.

Description

technical field [0001] The invention belongs to the technical field of integrated circuit hardware security, and in particular relates to a hardware Trojan horse detection method. Background technique [0002] In order to improve the efficiency of product development and shorten the time to market, modern integrated circuit designs use a large number of intellectual property (IP) cores provided by untrusted third parties. These IP cores may contain malicious design modifications outside the design specifications, that is, hardware Trojan horses. Hardware Trojans have the characteristics of light weight and high concealment. In order to avoid being discovered, hardware Trojans spend most of the time in a dormant state and will only be activated under certain conditions. Once the hardware Trojan is activated, it may cause abnormal functions of integrated circuits, performance degradation, leakage of sensitive information, and even remote control of the chips, posing a serious ...

AI Technical Summary

Problems solved by technology

However, the existing hardware Trojan detection methods based on machine learning rely on manually extracted circuit features, the detection accuracy is not high, and there are false positives.

Images