Fast and Accurate Identification of Hardware Trojan Locations in Gate-Level Netlist using Nearest Neighbour Approach integrated with Machine Learning Technique

2025-01-18

AI Summary

Precise hardware Trojan (HT) localization in gate-level netlists remains challenging in multi-party integrated circuit (IC) design due to structural complexity and limited observability. Method: This paper proposes a dual-granularity (graph-level and node-level) HT localization framework integrating k-nearest neighbors (k-NN) and graph neural networks (GNNs), featuring a novel NN-GNN collaborative architecture. It leverages first- and second-order NN models—rather than relying solely on GNNs—for enhanced detection sensitivity and interpretability. Path-based backtracking, principal component analysis (PCA), and decision-tree-based reasoning further improve model transparency. Contribution/Results: The second-order NN achieves 97.7% node-level localization accuracy—significantly outperforming the GNN baseline (79.8%)—and attains 62.8% graph-level accuracy. We uncover a fundamental trade-off between NN order and code coverage, enabling principled hyperparameter selection. Extensive evaluation across three representative multi-party design scenarios demonstrates strong robustness, scalability, and generalizability.

Technology Category

• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Data transparency and provenance

Abstract

In the evolving landscape of integrated circuit design, detecting Hardware Trojans (HTs) within a multi entity based design cycle presents significant challenges. This research proposes an innovative machine learning-based methodology for identifying malicious logic gates in gate-level netlists. By focusing on path retrace algorithms. The methodology is validated across three distinct cases, each employing different machine learning models to classify HTs. Case I utilizes a decision tree algorithm for node-to-node comparisons, significantly improving detection accuracy through the integration of Principal Component Analysis (PCA). Case II introduces a graph-to-graph classification using a Graph Neural Network (GNN) model, enabling the differentiation between normal and Trojan-infected circuit designs. Case III applies GNN-based node classification to identify individual compromised nodes and its location. Additionally, nearest neighbor (NN) method has been combined with GNN graph-to-graph in Case II and GNN node-to-node in Case III. Despite the potential of GNN model graph-to-graph classification, NN approach demonstrated superior performance, with the first nearest neighbor (1st NN) achieving 73.2% accuracy and the second nearest neighbor (2nd NN) method reaching 97.7%. In comparison, the GNN model achieved an accuracy of 62.8%. Similarly, GNN model node-to-node classification, NN approach demonstrated superior performance, with the 1st NN achieving 93% accuracy and the 2nd NN method reaching 97.7%. In comparison, the GNN model achieved an accuracy of 79.8%. However, higher and higher NN will lead to large code coverage for the identification of HTs.

Problem

• Identify Hardware Trojan locations in gate-level netlists
• Improve detection accuracy using machine learning techniques
• Compare performance of nearest neighbor and GNN methods

Innovation

• Machine learning for Hardware Trojan detection
• Nearest Neighbor approach enhances accuracy
• Graph Neural Network for node classification