Integrating Physical Unclonable Functions with Machine Learning for the Authentication of Edge Devices in IoT Networks

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Future Internet vol. 17, no. 7 (2025), p. 275-310
1. Verfasser: Sheikh Abdul Manan
Weitere Verfasser: Islam, Md Rafiqul, Habaebi Mohamed Hadi, Zabidi Suriza Ahmad, Bin Najeeb Athaur Rahman, Kabbani Adnan
Veröffentlicht:
MDPI AG
Schlagworte:
Online-Zugang:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!

MARC

LEADER 00000nab a2200000uu 4500
001 3233189351
003 UK-CbPIL
022 |a 1999-5903 
024 7 |a 10.3390/fi17070275  |2 doi 
035 |a 3233189351 
045 2 |b d20250101  |b d20251231 
084 |a 231464  |2 nlm 
100 1 |a Sheikh Abdul Manan  |u Department of Electrical Engineering and Computer Science, College of Engineering, A’Sharqiyah University, Ibra 400, Oman; kabbani_a@asu.edu.om 
245 1 |a Integrating Physical Unclonable Functions with Machine Learning for the Authentication of Edge Devices in IoT Networks 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Edge computing (EC) faces unique security threats due to its distributed architecture, resource-constrained devices, and diverse applications, making it vulnerable to data breaches, malware infiltration, and device compromise. The mitigation strategies against EC data security threats include encryption, secure authentication, regular updates, tamper-resistant hardware, and lightweight security protocols. Physical Unclonable Functions (PUFs) are digital fingerprints for device authentication that enhance interconnected devices’ security due to their cryptographic characteristics. PUFs produce output responses against challenge inputs based on the physical structure and intrinsic manufacturing variations of an integrated circuit (IC). These challenge-response pairs (CRPs) enable secure and reliable device authentication. Our work implements the Arbiter PUF (APUF) on Altera Cyclone IV FPGAs installed on the ALINX AX4010 board. The proposed APUF has achieved performance metrics of 49.28% uniqueness, 38.6% uniformity, and 89.19% reliability. The robustness of the proposed APUF against machine learning (ML)-based modeling attacks is tested using supervised Support Vector Machines (SVMs), logistic regression (LR), and an ensemble of gradient boosting (GB) models. These ML models were trained over more than 19K CRPs, achieving prediction accuracies of 61.1%, 63.5%, and 63%, respectively, thus cementing the resiliency of the device against modeling attacks. However, the proposed APUF exhibited its vulnerability to Multi-Layer Perceptron (MLP) and random forest (RF) modeling attacks, with 95.4% and 95.9% prediction accuracies, gaining successful authentication. APUFs are well-suited for device authentication due to their lightweight design and can produce a vast number of challenge-response pairs (CRPs), even in environments with limited resources. Our findings confirm that our approach effectively resists widely recognized attack methods to model PUFs. 
653 |a Collaboration 
653 |a Multilayers 
653 |a Communication 
653 |a Cementing 
653 |a Modelling 
653 |a Multilayer perceptrons 
653 |a Real time 
653 |a Edge computing 
653 |a Data processing 
653 |a Privacy 
653 |a Machine learning 
653 |a Access control 
653 |a Internet of Things 
653 |a Field programmable gate arrays 
653 |a Business metrics 
653 |a Accuracy 
653 |a Data integrity 
653 |a Performance measurement 
653 |a Artificial intelligence 
653 |a Integrated circuits 
653 |a Support vector machines 
653 |a Reliability 
653 |a Sensors 
653 |a Decision making 
653 |a Design 
653 |a Blockchain 
653 |a Integrated approach 
653 |a Cloud computing 
653 |a Authentication 
653 |a Data transmission 
653 |a Cybersecurity 
700 1 |a Islam, Md Rafiqul  |u Department of Electrical Computer Engineering, Kulliyyah of Engineering, International Islamic University, Kuala Lumpur 53100, Malaysia; rafiq@iium.edu.my (M.R.I.); suriza@iium.edu.my (S.A.Z.); athaur@iium.edu.my (A.R.B.N.) 
700 1 |a Habaebi Mohamed Hadi  |u Department of Electrical Computer Engineering, Kulliyyah of Engineering, International Islamic University, Kuala Lumpur 53100, Malaysia; rafiq@iium.edu.my (M.R.I.); suriza@iium.edu.my (S.A.Z.); athaur@iium.edu.my (A.R.B.N.) 
700 1 |a Zabidi Suriza Ahmad  |u Department of Electrical Computer Engineering, Kulliyyah of Engineering, International Islamic University, Kuala Lumpur 53100, Malaysia; rafiq@iium.edu.my (M.R.I.); suriza@iium.edu.my (S.A.Z.); athaur@iium.edu.my (A.R.B.N.) 
700 1 |a Bin Najeeb Athaur Rahman  |u Department of Electrical Computer Engineering, Kulliyyah of Engineering, International Islamic University, Kuala Lumpur 53100, Malaysia; rafiq@iium.edu.my (M.R.I.); suriza@iium.edu.my (S.A.Z.); athaur@iium.edu.my (A.R.B.N.) 
700 1 |a Kabbani Adnan  |u Department of Electrical Engineering and Computer Science, College of Engineering, A’Sharqiyah University, Ibra 400, Oman; kabbani_a@asu.edu.om 
773 0 |t Future Internet  |g vol. 17, no. 7 (2025), p. 275-310 
786 0 |d ProQuest  |t ABI/INFORM Global 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3233189351/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3233189351/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3233189351/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch