Embracing Graph Neural Networks for Hardware Security (Invited Paper)

TL;DR

This paper surveys the application of graph neural networks in hardware security, highlighting their effectiveness in detecting IP piracy, hardware Trojans, and reverse engineering, and providing a taxonomy of current methods.

Contribution

It introduces the first taxonomy categorizing GNN-based hardware security systems and summarizes architectures, datasets, and evaluation methods used in the field.

Findings

GNNs achieve state-of-the-art results in hardware security tasks

The survey categorizes GNN applications into four main groups

Discussion of future research directions in GNN-based security

Abstract

Graph neural networks (GNNs) have attracted increasing attention due to their superior performance in deep learning on graph-structured data. GNNs have succeeded across various domains such as social networks, chemistry, and electronic design automation (EDA). Electronic circuits have a long history of being represented as graphs, and to no surprise, GNNs have demonstrated state-of-the-art performance in solving various EDA tasks. More importantly, GNNs are now employed to address several hardware security problems, such as detecting intellectual property (IP) piracy and hardware Trojans (HTs), to name a few. In this survey, we first provide a comprehensive overview of the usage of GNNs in hardware security and propose the first taxonomy to divide the state-of-the-art GNN-based hardware security systems into four categories: (i) HT detection systems, (ii) IP piracy detection systems, (iii) reverse engineering platforms, and (iv) attacks on logic locking. We summarize the different architectures, graph types, node features, benchmark data sets, and model evaluation of the employed GNNs. Finally, we elaborate on the lessons learned and discuss future directions.