Early Detection of Hardware Trojans Using Neural Controlled Differential Equations and Analysis of Power Traces

2026-07-25

AI Summary

This study addresses the critical challenge of detecting dormant adaptive hardware Trojans prior to activation—a task that existing methods struggle with, posing significant security risks. To overcome this limitation, the work introduces neural controlled differential equations (NCDEs) for early Trojan detection, modeling normal circuit behavior exclusively from power consumption data of Trojan-free designs. By integrating linear discriminant analysis (LDA) with sliding-window temporal analysis, the proposed approach achieves high-accuracy classification among three states: Trojan-free, dormant Trojan, and activated Trojan. Notably, it circumvents the conventional reliance on post-activation features and demonstrates superior performance over state-of-the-art machine learning techniques on standard benchmarks, effectively identifying dormant Trojans whose signatures exceed a defined sensitivity threshold.

Abstract

Evolving Hardware Trojans pose a serious threat to modern digital systems by evading traditional detection through stealthy, adaptive behavior. Even recent methods that leverage advances in machine learning can only detect them after activation, leaving a critical window for potential security breaches. To address this gap, we propose a novel approach for hardware Trojan detection and prediction using Neural Controlled Differential Equations (NCDEs) and analysis of power traces. Our method leverages an NCDE model trained exclusively on Trojan-free data to learn nominal power behavior, combined with a Linear Discriminant Analysis (LDA) classifier calibrated on labeled data, to distinguish between three scenarios: no Trojan, dormant Trojan, and active Trojan. Our method uses a sliding window to process side-channel measurements, enabling detection of subtle power consumption deviations that indicate Trojan presence, even when dormant. Experimental results demonstrate that the proposed NCDE-based method achieves superior accuracy compared to traditional machine learning approaches, with the additional advantage of handling dormant Trojans above a sensitivity threshold. We validate our approach on standard hardware Trojan benchmarks, showing robust detection and prediction performance.

Problem

• Hardware Trojans
• Early Detection
• Power Traces
• Dormant Trojans
• Security Breaches

Innovation

• Neural Controlled Differential Equations
• Hardware Trojan Detection
• Power Trace Analysis
• Dormant Trojan Prediction
• Side-channel Analysis