Hardware Trojan horse detection method and system based on bidirectional graph convolutional neural network

Abstract

The invention relates to a hardware Trojan horse detection method and system based on a bidirectional graph convolutional neural network. The method comprises the following steps of firstly, preprocessing a netlist file, creating a corresponding directed graph representation, encoding gate device information as a feature representation X, and constructing circuit directed graph data, respectively creating a forward circuit diagram for describing a circuit signal propagation structure and a reverse circuit diagram for describing a circuit signal dispersion structure, respectively constructing corresponding graph neural network feature extractors to extract structural features, and combining the structural features into final gate device features, constructing a multi-layer perceptron classification model, forming a hardware Trojan horse gate classification model by the multi-layer perceptron classification model and a graph neural network feature extractor, and learning model parameters by using a weighted cross entropy loss function to obtain a trained hardware Trojan horse gate classification model, and converting a to-be-detected netlist into a directed graph, inputting the directed graph into the trained hardware Trojan horse gate classification model for detection, and outputting a suspicious door device list. According to the method, the exit-level hardware Trojan horse can be effectively detected.

Description

technical field [0001] The invention relates to the field of hardware Trojan horse detection, in particular to a hardware Trojan horse detection method and system based on a bidirectional graph convolutional neural network. Background technique [0002] The chip is the basis of the physical network system. With the rapid development of the network, the popularity of electronic equipment is getting higher and higher, and the chip is widely used in different fields. However, due to the high cost and intense competitive pressure, the production process of the chip usually requires the joint participation of multiple manufacturers, which makes it easy for attackers to implant hardware Trojans in the design of large-scale integrated circuits to perform specific malicious operations, resulting in major security risks and damage. Hardware Trojans are mainly implanted in the chip design stage, and the detection cost after chip manufacturing is often very expensive, so it is very im...

AI Technical Summary

Problems solved by technology

Since each level of leap may be implanted into a hardware Trojan horse, the closer to the manufacturing stage the detection has a more defensive effect, but the lower the abstraction level, the more design details, accompanied by the increase in complexity

Most of the current detection work is concentrated on the register transfer level, and it is difficult to detect and locate the relevant Trojan horse structure in large-scale integrated circuits

In general, there is no efficient, automatic and easy-to-expand hardware Trojan detection method and system for the gate level.

Images