Secure medical treatment with deep learning on embedded board

Abdaoui, Abderrazak; Al-Ali, Abdulla; Riahi, Aref; Mohamed, Amr; Du, Xiaojiang; Guizani, Mohsen

doi:10.1016/b978-0-12-819045-6.00007-8

Cited by 8 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results illustrated that the proposed system had a high Detection Rate and low FPR for three medical datasets. Furthermore, referring to the security of signals from deep brain stimulators, the authors in Abdaoui et al (2020) built a system for distinguishing false alarms from legitimate ones and classified the attacks using Raspberry Pi3 and deep learning. It was found that deep learning can show an accuracy of about 97% to learn and predict the fake signals.…”

Section: Results and Findingsmentioning

confidence: 99%

A systematic review of security and privacy issues in the internet of medical things; the role of machine learning approaches

Hameed

Hassan

Latiff

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Background The Internet of Medical Things (IoMTs) is gradually replacing the traditional healthcare system. However, little attention has been paid to their security requirements in the development of the IoMT devices and systems. One of the main reasons can be the difficulty of tuning conventional security solutions to the IoMT system. Machine Learning (ML) has been successfully employed in the attack detection and mitigation process. Advanced ML technique can also be a promising approach to address the existing and anticipated IoMT security and privacy issues. However, because of the existing challenges of IoMT system, it is imperative to know how these techniques can be effectively utilized to meet the security and privacy requirements without affecting the IoMT systems quality, services, and device’s lifespan. Methodology This article is devoted to perform a Systematic Literature Review (SLR) on the security and privacy issues of IoMT and their solutions by ML techniques. The recent research papers disseminated between 2010 and 2020 are selected from multiple databases and a standardized SLR method is conducted. A total of 153 papers were reviewed and a critical analysis was conducted on the selected papers. Furthermore, this review study attempts to highlight the limitation of the current methods and aims to find possible solutions to them. Thus, a detailed analysis was carried out on the selected papers through focusing on their methods, advantages, limitations, the utilized tools, and data. Results It was observed that ML techniques have been significantly deployed for device and network layer security. Most of the current studies improved traditional metrics while ignored performance complexity metrics in their evaluations. Their studies environments and utilized data barely represent IoMT system. Therefore, conventional ML techniques may fail if metrics such as resource complexity and power usage are not considered.

show abstract

Section: Results and Findingsmentioning

confidence: 99%

A systematic review of security and privacy issues in the internet of medical things; the role of machine learning approaches

Hameed

Hassan

Latiff

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…IoMT layer-Ref Supervised ML -Implantable, wearable Sensor layer-{ (Haque, Rahman and Aziz 2015) , (Abdaoui et al 2020) , (Khan et al 2017), (Gao and Thamilarasu 2017), (Newaz et al 2019), (Ben Amor, Lahyani and Jmaiel 2020), (Mohamed, Meddeb-Makhlouf and Fakhfakh 2019), (Salem et al 2014), (Hau and Lupu 2019), (Nagdeo and Mahapatro 2019), (Verner and Butvinik (Mawgoud et al 2019), (Barros et al 2019), (Zhang et al 2018), (Shang & Wu 2019), (Musale et al 2019), (Vhaduri & Poellabauer 2019), (Mohsen et al 2019), (Rathore et al 2018a) } Network layer-{(Begli, Derakhshan and Karimipour 2019), (Itten and Vadakkumcheril 2016), (Schneble and Thamilarasu 2019), (Odesile and Thamilarasu 2017), (RM et al 2020), (Asfaw et al 2010), (Alrashdi et al 2019), (Wazid et al 2019) Manuscript to be reviewed…”

Section: Category -Medical Device Categorymentioning

confidence: 99%

Peer Review #3 of "A systematic review of security and privacy issues in the internet of medical things; the role of machine learning approaches (v0.2)"

2021

View full text Add to dashboard Cite

Background . The Internet of Medical Things (IoMTs) is gradually replacing the traditional healthcare system. However, little attention has been paid to their security requirements in the development of the IoMT devices and systems. One of the main reasons can be the difficulty of tuning conventional security solutions to the IoMT system. Machine Learning (ML) has been successfully employed in the attack detection and mitigation process. Advanced ML technique can also be a promising approach to address the existing and anticipated IoMT security and privacy issues. However, because of the existing challenges of IoMT system, it is imperative to know how these techniques can be effectively utilized to meet the security and privacy requirements without affecting the IoMT systems quality, services, and device's lifespan.Methodology. This paper is devoted to perform a Systematic Literature Review (SLR) on the security and privacy issues of IoMT and their solutions by ML techniques. The recent research papers disseminated between 2010 to 2020 are selected from multiple databases and a standardized SLR method is conducted. A total of 153 papers were reviewed and a critical analysis were conducted on the selected papers. Furthermore, this review study attempts to highlight the limitation of the current methods and aims to find possible solutions to them. Thus, a detailed analysis was carried out on the selected papers through focusing on their methods, advantages, limitations, the utilized tools, and data. Results.It was observed that ML techniques have been significantly deployed for device and network layer security. Most of the current studies improved traditional metrics while ignored performance complexity metrics in their evaluations. Their studies environments and utilized data barely represent IoMT system. Therefore, conventional ML techniques may fail if metrics such as resource complexity and power usage are not considered.

show abstract

“…It was seen that the system did not impose extra overhead on medical devices. Moreover, edge devices such as Raspberry Pi3 and deep learning (DL) were used for detecting false data injections in the implantable brain devices [33]. In another study, multi-layer perceptron (MLP) and field-programmable gate array (FPGA) chips were used for attack detection in insulin pumps [34].…”

Section: Stationarymentioning

confidence: 99%

A Hybrid Lightweight System for Early Attack Detection in the IoMT Fog

Hameed

Selamat

Latiff

et al. 2021

Sensors

View full text Add to dashboard Cite

Cyber-attack detection via on-gadget embedded models and cloud systems are widely used for the Internet of Medical Things (IoMT). The former has a limited computation ability, whereas the latter has a long detection time. Fog-based attack detection is alternatively used to overcome these problems. However, the current fog-based systems cannot handle the ever-increasing IoMT’s big data. Moreover, they are not lightweight and are designed for network attack detection only. In this work, a hybrid (for host and network) lightweight system is proposed for early attack detection in the IoMT fog. In an adaptive online setting, six different incremental classifiers were implemented, namely a novel Weighted Hoeffding Tree Ensemble (WHTE), Incremental K-Nearest Neighbors (IKNN), Incremental Naïve Bayes (INB), Hoeffding Tree Majority Class (HTMC), Hoeffding Tree Naïve Bayes (HTNB), and Hoeffding Tree Naïve Bayes Adaptive (HTNBA). The system was benchmarked with seven heterogeneous sensors and a NetFlow data infected with nine types of recent attack. The results showed that the proposed system worked well on the lightweight fog devices with ~100% accuracy, a low detection time, and a low memory usage of less than 6 MiB. The single-criteria comparative analysis showed that the WHTE ensemble was more accurate and was less sensitive to the concept drift.

show abstract

Secure medical treatment with deep learning on embedded board

Cited by 8 publications

References 16 publications

A systematic review of security and privacy issues in the internet of medical things; the role of machine learning approaches

A systematic review of security and privacy issues in the internet of medical things; the role of machine learning approaches

Peer Review #3 of "A systematic review of security and privacy issues in the internet of medical things; the role of machine learning approaches (v0.2)"

A Hybrid Lightweight System for Early Attack Detection in the IoMT Fog

Contact Info

Product

Resources

About