TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs

2025-06-22

AI Summary

Existing hardware Trojan (HT) detection methods for large-scale RTL designs suffer from low detection accuracy, poor cross-scale generalization, and insufficient training/inference efficiency. Method: This paper proposes a graph neural network (GNN)-based framework tailored for HT detection. Specifically: (i) it constructs an RTL-level circuit graph model compatible with diverse GNN architectures; (ii) it introduces a task-specific GNN quantization strategy that significantly improves training and inference efficiency on large designs; and (iii) it implements an end-to-end detection pipeline supporting security verification of complex IPs (e.g., RISC-V). Contribution/Results: The work overcomes the scalability bottleneck of prior GNN-based approaches and is the first to systematically investigate the impact of GNN architecture selection and quantization on HT detection performance. Evaluated on a custom dataset, the framework achieves 98.66% precision and 92.30% recall, demonstrating both high efficiency and practical applicability.

Technology Category

• Machine Learning: Hardware-aware ML
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Chip manufacturing is a complex process, and to achieve a faster time to market, an increasing number of untrusted third-party tools and designs from around the world are being utilized. The use of these untrusted third party intellectual properties (IPs) and tools increases the risk of adversaries inserting hardware trojans (HTs). The covert nature of HTs poses significant threats to cyberspace, potentially leading to severe consequences for national security, the economy, and personal privacy. Many graph neural network (GNN)-based HT detection methods have been proposed. However, they perform poorly on larger designs because they rely on training with smaller designs. Additionally, these methods do not explore different GNN models that are well-suited for HT detection or provide efficient training and inference processes. We propose a novel framework that generates graph embeddings for large designs (e.g., RISC-V) and incorporates various GNN models tailored for HT detection. Furthermore, our framework introduces domain-specific techniques for efficient training and inference by implementing model quantization. Model quantization reduces the precision of the weights, lowering the computational requirements, enhancing processing speed without significantly affecting detection accuracy. We evaluate our framework using a custom dataset, and our results demonstrate a precision of 98.66% and a recall (true positive rate) of 92.30%, highlighting the effectiveness and efficiency of our approach in detecting hardware trojans in large-scale chip designs

Problem

• Detect hardware trojans in large RTL designs
• Improve GNN-based HT detection for scalability
• Optimize training and inference with model quantization

Innovation

• GNN models for HT detection in RTL
• Graph embeddings for large chip designs
• Model quantization boosts efficiency