Reference-Free EM Validation Flow for Detecting Triggered Hardware Trojans

TL;DR

This paper presents a novel reference-free EM-based detection framework for triggered hardware Trojans in integrated circuits, leveraging deep learning and statistical modeling to identify anomalies without needing pre-labeled data.

Contribution

It introduces a design-agnostic, reference-free detection flow combining wavelet transforms, CNN feature extraction, PCA, and Bayesian clustering for reliable HT detection.

Findings

High separability between HT-free and HT-activated states demonstrated

Robust detection performance across different PCA variance thresholds

Framework scalable and interpretable for in-field HT monitoring

Abstract

Hardware Trojans (HTs) threaten the trust and reliability of integrated circuits (ICs), particularly when triggered HTs remain dormant during standard testing and activate only under rare conditions. Existing electromagnetic (EM) side-channel-based detection techniques often rely on golden references or labeled data, which are infeasible in modern distributed manufacturing. This paper introduces a reference-free, design-agnostic framework for detecting triggered HTs directly from post-silicon EM emissions. The proposed flow converts each EM trace into a time-frequency scalogram using Continuous Wavelet Transform (CWT), extracts discriminative features through a convolutional neural network (CNN), reduces dimensionality with principal component analysis (PCA), and applies Bayesian Gaussian Mixture Modeling (BGMM) for unsupervised probabilistic clustering. The framework quantifies detection confidence using posterior-based metrics (alpha_{post}, beta_{post}), Bayesian information criterion (Delta BIC), and Mahalanobis cluster separation (D), enabling interpretable anomaly decisions without golden data. Experimental validation on AES-128 designs embedded with four different HTs demonstrates high separability between HT-free and HT-activated conditions and robustness to PCA variance thresholds. The results highlight the method's scalability, statistical interpretability, and potential for extension to runtime and in-field HT monitoring in trusted microelectronics.