Secure and interpretable dyslexia detection using homomorphic encryption and SHAP-based explanations

Basit Öğe Kaydı
dc.authorid0009-0001-4214-8738
dc.authorid0000-0003-2865-6370
dc.authorid0009-0007-8239-8604
dc.contributor.authorHarb, Mhd Raja Abouen_US
dc.contributor.authorÇeliktaş, Barışen_US
dc.contributor.authorEroğlu, Güneten_US
dc.date.accessioned2026-03-06T10:23:00Z
dc.date.available2026-03-06T10:23:00Z
dc.date.issued2025-10-25
dc.departmentIşık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programı en_US
dc.departmentIşık University, School of Graduate Studies, Master’s Program in Computer Engineeringen_US
dc.departmentIşık Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering and Natural Sciences, Department of Computer Engineeringen_US
dc.description.abstractProtecting sensitive healthcare data during machine learning inference is critical, particularly in cloud-based environments. This study addresses the privacy and interpretability challenges in dyslexia detection using Quantitative EEG (QEEG) data. We propose a privacy-preserving framework utilizing Homomorphic Encryption (HE) to securely perform inference with an Artificial Neural Network (ANN). Due to the incompatibility of non-linear activation functions with encrypted arithmetic, we employ a dedicated approximation strategy. To ensure model interpretability without compromising privacy, SHapley Additive exPlanations (SHAP) are computed homomorphically and decrypted client-side. Experimental evaluations demonstrate that the encrypted inference achieves an accuracy of 90.03% and an AUC of 0.8218, reflecting only minor performance degradation compared to plaintext inference. SHAP value comparisons (Spearman correlation = 0.59) validate the reliability of the encrypted explanations. These results confirm that integrating privacy-preserving and explainable AI approaches is feasible for secure, ethical, and compliant healthcare deployments.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationHarb, M. R. A., Çeliktaş, B. & Eroğlu, G. (2025). Secure and interpretable dyslexia detection using homomorphic encryption and SHAP-based explanations. Paper presented at the TIPTEKNO 2025 - Medical Technologies Congress, Proceedings, 1-4. doi:https://doi.org/10.1109/TIPTEKNO68206.2025.11270026en_US
dc.identifier.doi10.1109/TIPTEKNO68206.2025.11270026
dc.identifier.endpage4
dc.identifier.isbn9798331555658
dc.identifier.scopus2-s2.0-105030542241
dc.identifier.scopusqualityN/A
dc.identifier.startpage1
dc.identifier.urihttps://hdl.handle.net/11729/7104
dc.identifier.urihttps://doi.org/10.1109/TIPTEKNO68206.2025.11270026
dc.indekslendigikaynakScopusen_US
dc.institutionauthorHarb, Mhd Raja Abouen_US
dc.institutionauthorÇeliktaş, Barışen_US
dc.institutionauthorid0009-0001-4214-8738
dc.institutionauthorid0000-0003-2865-6370
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofTIPTEKNO 2025 - Medical Technologies Congress, Proceedingsen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Öğrencien_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDyslexia detectionen_US
dc.subjectEncrypted inferenceen_US
dc.subjectExplainable Artificial Intelligence (XAI)en_US
dc.subjectHomomorphic encryptionen_US
dc.subjectQuantitative EEG (QEEG)en_US
dc.subjectSHAPen_US
dc.subjectComputation theoryen_US
dc.subjectInference enginesen_US
dc.subjectLearning systemsen_US
dc.subjectMedical computingen_US
dc.subjectPrivacy-preserving techniquesen_US
dc.subjectDyslexium detectionen_US
dc.subjectHo-momorphic encryptionsen_US
dc.subjectHomomorphic-encryptionsen_US
dc.subjectInterpretabilityen_US
dc.subjectPrivacy preservingen_US
dc.subjectShapleyen_US
dc.subjectShapley additive explanationen_US
dc.subjectNeural networksen_US
dc.titleSecure and interpretable dyslexia detection using homomorphic encryption and SHAP-based explanationsen_US
dc.typeConference Objecten_US
dspace.entity.typePublicationen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Secure_and_Interpretable_Dyslexia_Detection_Using_Homomorphic_Encryption_and_SHAP_Based_Explanations.pdf
Boyut:
1.22 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Öğrenci Yayınları Bildiri Koleksiyonu
Bildiri Koleksiyonu | Bilgisayar Mühendisliği Bölümü
Lisansüstü Eğitim Enstitüsü Diğer Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu