Using Machine Learning for Dynamic Authentication in Telehealth: A Tutorial

Fard, Seyed Mehdi Hazrati; Gebali, Fayez; Mamun, Mohammad Saiful Islam

doi:10.3390/s22197655

Cited by 18 publications

(8 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One solution to this problem is to utilize ML to process biometric information or physical layer features for human and IoT device authentication, respectively. This tutorial [24] discusses the use of ML in the creation of robust authentication protocols. These methods, which are trained on hidden concepts in biometric and physical layer data, can provide more reliable dynamic authentication models than traditional methods.…”

Section: Related Workmentioning

confidence: 99%

“…2FA can also provide privacy protection and allow for mutual authentication and session key negotiation with minimal computational cost [23], [26]. In addition, the use of ML in the creation of robust authentication protocols can provide more reliable dynamic authentication models, as well as continuous and context-aware authentication [24]. There are also several challenges and limitations to consider when implementing these approaches.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Wi-Fi Radio Wave-Based Continuous Zero-Effort Two-Factor Authentication Utilizes Machine Learning

AlQahtani¹,

Alshayeb²

2023

Preprint

View full text Add to dashboard Cite

<p>Two-factor authentication (2FA) is a widely adopted security measure that requires users to provide an additional layer of authentication beyond a username and password in order to access protected resources. While traditional 2FA methods rely on the user to manually enter a code or token, the use of machine learning (ML) has the potential to revolutionize 2FA by enabling automatic and continuous verification of a user’s identity. In this paper, we propose a continuous zero effort 2FA system that uses ML to verify a user’s identity based on the unique characteristics of their environment, including beacon frame characteristics and RSSI values collected from Wi-Fi access points (APs). This system allows for seamless and automatic authentication without requiring any additional input or action from the user beyond their initial login. Additionally, the continuous authentication feature of the proposed system ensures that access to protected resources is maintained only when the user’s two devices are co-located. Through experiments, we demonstrate the effectiveness of the proposed system in determining the location of the user’s devices based on beacon frame characteristics and Received Signal Strength Indicator (RSSI) values. The proposed system offers a convenient and secure solution for 2FA that utilizes the power of ML to enable automatic and continuous authentication. Furthermore, its scalability, flexibility, and adjustability make it a promising option for organizations and users who need a secure and convenient authentication system. Finally, we have included three Python codes in the appendix, which provide further insights into our evaluation and analysis of the proposed system.</p>

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Wi-Fi Radio Wave-Based Continuous Zero-Effort Two-Factor Authentication Utilizes Machine Learning

AlQahtani¹,

Alshayeb²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Kashou et al compared the ability of ML and deep neural networks (DNNs) using ECG signals for authentication [ 12 ]. Developing a verification model for user identification using ML and DLLs offers many advantages, such as being human-independent, cost-effective, reliable, faster, and more precise [ 15 ]. Numerous ML models have been developed for biometric-based authentication systems, with DNNs being widely applied in this area recently [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

“… Most ML models are sensitive to imbalanced datasets [ 18 ]. Enrolling a new entity in the system is complex because of the need to train the model from scratch [ 15 ]. …”

Section: Introductionmentioning

confidence: 99%

Ensemble Siamese Network (ESN) Using ECG Signals for Human Authentication in Smart Healthcare System

Fard

Agrawal

Gebali

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Advancements in digital communications that permit remote patient visits and condition monitoring can be attributed to a revolution in digital healthcare systems. Continuous authentication based on contextual information offers a number of advantages over traditional authentication, including the ability to estimate the likelihood that the users are who they claim to be on an ongoing basis over the course of an entire session, making it a much more effective security measure for proactively regulating authorized access to sensitive data. Current authentication models that rely on machine learning have their shortcomings, such as the difficulty in enrolling new users to the system or model training sensitivity to imbalanced datasets. To address these issues, we propose using ECG signals, which are easily accessible in digital healthcare systems, for authentication through an Ensemble Siamese Network (ESN) that can handle small changes in ECG signals. Adding preprocessing for feature extraction to this model can result in superior results. We trained this model on ECG-ID and PTB benchmark datasets, achieving 93.6% and 96.8% accuracy and 1.76% and 1.69% equal error rates, respectively. The combination of data availability, simplicity, and robustness makes it an ideal choice for smart healthcare and telehealth.

show abstract

“…Machine Learning (ML) is one of the most successful tools used in various fi elds to solve problems. ML methods are adopted to develop a verifi cation model for user identifi cation [6]. Our model will do it by getting the user's ECG dataset.…”

Section: Introductionmentioning

confidence: 99%

Using ECG Signals in Siamese Networks for Authentication in Digital Healthcare Systems

Behrouzi¹,

Shirkani²,

Fard³

2022

J Biomed Res Environ Sci

View full text Add to dashboard Cite

In digital healthcare systems, with digitalization, data can be easily accessed. Considering the sensitivity of confidential information, the need for security is accelerated during this time. One of the most important security aspects is authentication which should be utilized. The available authentication models that rely on Machine Learning (ML) have some shortcomings, such as difficulties in appending new users to the system or model training sensitivity to imbalanced data. To address these problems, we propose an application of the Siamese networks using ECG signals which are easily reachable in digital healthcare systems. Adding some preprocessing for feature extraction in such a model could lead us to prominent results. This model is performed on ECD-ID and PTB datasets and approaches 92% and 95% of accuracy, respectively. A combination of simplicity and high performance made it an exclusive choice for smart healthcare and telehealth.

show abstract

Using Machine Learning for Dynamic Authentication in Telehealth: A Tutorial

Cited by 18 publications

References 84 publications

Wi-Fi Radio Wave-Based Continuous Zero-Effort Two-Factor Authentication Utilizes Machine Learning

Wi-Fi Radio Wave-Based Continuous Zero-Effort Two-Factor Authentication Utilizes Machine Learning

Ensemble Siamese Network (ESN) Using ECG Signals for Human Authentication in Smart Healthcare System

Using ECG Signals in Siamese Networks for Authentication in Digital Healthcare Systems

Contact Info

Product

Resources

About