A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout

<p dir="ltr">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)...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Arash Golabi (21841484) (author)
مؤلفون آخرون: Abdelkarim Erradi (13475740) (author), Ahmed Bensaid (21259505) (author), Abdulla Al-Ali (22502837) (author), Uvais Qidwai (16888698) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513533686841344
author Arash Golabi (21841484)
author2 Abdelkarim Erradi (13475740)
Ahmed Bensaid (21259505)
Abdulla Al-Ali (22502837)
Uvais Qidwai (16888698)
author2_role author
author
author
author
author_facet Arash Golabi (21841484)
Abdelkarim Erradi (13475740)
Ahmed Bensaid (21259505)
Abdulla Al-Ali (22502837)
Uvais Qidwai (16888698)
author_role author
dc.creator.none.fl_str_mv Arash Golabi (21841484)
Abdelkarim Erradi (13475740)
Ahmed Bensaid (21259505)
Abdulla Al-Ali (22502837)
Uvais Qidwai (16888698)
dc.date.none.fl_str_mv 2025-05-25T09:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s10207-025-01049-5
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_dual-stage_deep_learning_approach_for_robust_detection_and_identification_of_hardware_trojans_using_monte-carlo_dropout/30454991
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Cybersecurity and privacy
Machine learning
Hardware trojan detection
Time series analysis
Markov transition field
Convolutional neural networks
Deep neural networks
dc.title.none.fl_str_mv A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">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.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Information Security<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s10207-025-01049-5" target="_blank">https://dx.doi.org/10.1007/s10207-025-01049-5</a></p>
eu_rights_str_mv openAccess
id Manara2_3e2ae06c57a98d988c637756880ad944
identifier_str_mv 10.1007/s10207-025-01049-5
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30454991
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropoutArash Golabi (21841484)Abdelkarim Erradi (13475740)Ahmed Bensaid (21259505)Abdulla Al-Ali (22502837)Uvais Qidwai (16888698)Information and computing sciencesCybersecurity and privacyMachine learningHardware trojan detectionTime series analysisMarkov transition fieldConvolutional neural networksDeep neural networks<p dir="ltr">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.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Information Security<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s10207-025-01049-5" target="_blank">https://dx.doi.org/10.1007/s10207-025-01049-5</a></p>2025-05-25T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s10207-025-01049-5https://figshare.com/articles/journal_contribution/A_dual-stage_deep_learning_approach_for_robust_detection_and_identification_of_hardware_trojans_using_monte-carlo_dropout/30454991CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/304549912025-05-25T09:00:00Z
spellingShingle A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
Arash Golabi (21841484)
Information and computing sciences
Cybersecurity and privacy
Machine learning
Hardware trojan detection
Time series analysis
Markov transition field
Convolutional neural networks
Deep neural networks
status_str publishedVersion
title A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
title_full A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
title_fullStr A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
title_full_unstemmed A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
title_short A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
title_sort A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout
topic Information and computing sciences
Cybersecurity and privacy
Machine learning
Hardware trojan detection
Time series analysis
Markov transition field
Convolutional neural networks
Deep neural networks