A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
Open Access
- 25 May 2025
- journal article
- regular contribution
- Published by Springer Nature in International Journal of Information Security
- Vol. 24 (3) , 1-20
Abstract
Hardware Trojans (HTs) pose a significant threat to the integrity and security of integrated circuits, particularly in critical systems where stealthy hardware modifications can lead to catastrophic consequences. Detecting such Trojans through side-channel analysis (SCA) remains a major challenge due to subtle signal variations and environmental noise. This paper presents a dual-path deep learning framework for the detection and identification of HTs via side-channel analysis. The proposed approach transforms time-series side-channel data- including power consumption, electromagnetic emissions, and timing information-into two distinct image-based representations using Markov Transition Fields (MTF) and a reshaping technique. These transformed representations feed into a two-stage architecture: an Attack Detector, which determines the presence of an HT, and an Attack Identifier, which classifies the specific type of detected HT. To enhance reliability, Monte Carlo Dropout (MCD) is integrated for uncertainty estimation, enabling the framework to flag low-confidence detections and support more robust decision-making. The proposed method is evaluated on publicly available AES hardware Trojan datasets from TrustHub and IEEE Dataport, demonstrating superior accuracy over existing approaches, particularly for complex HT variants with subtle attack signatures. Furthermore, the robustness of the proposed method has been assessed by introducing noise into the validation dataset to simulate real-world operational perturbations such as process variation, aging, and voltage level variations. The results demonstrate the effectiveness and applicability of the dual-path deep learning framework for hardware Trojan detection.Keywords
Funding Information
- Qatar University
This publication has 56 references indexed in Scilit:
- An ensemble learning model for hardware Trojan detection in integrated circuit designComputers and Electrical Engineering, 2025
- Hardware Trojans Detection and Prevention Techniques ReviewWireless Personal Communications, 2024
- Performance prediction in online academic course: a deep learning approach with time series imagingMultimedia Tools and Applications, 2023
- Threshold Analysis Using Probabilistic Xgboost Classifier for Hardware Trojan DetectionJournal of Electronic Testing, 2023
- A comprehensive survey of physical and logic testing techniques for Hardware Trojan detection and preventionJournal of Cryptographic Engineering, 2022
- Time Series Classification Based on Image Transformation Using Feature Fusion StrategyNeural Processing Letters, 2022
- Convolutional neural network for stock trading using technical indicatorsAutomated Software Engineering, 2022
- Introduction to Hardware Trojans2017
- Logic Testing for Hardware Trojan Detection2017
- Detection and Diagnosis of Hardware Trojan Using Power Analysis2015