Reprint of : LEGIoT: A Lightweight Edge Gateway for the Internet of Things

Morabito, Roberto; Petrolo, Riccardo; Loscrì, Valeria; Mitton, Nathalie

doi:10.1016/j.future.2018.10.020

Cited by 14 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the principle of subsystem isolation goes well beyond physical or subsystem interfaces isolation. IoT deployments now make extensive use of containerisation technologies and IoT devices can themselves be put under this context through container engines and container APIs [88], which can link endpoint devices to an extended system of IoT-enabled application services [89]. Significant ongoing research currently targets the extension of IoT resources orchestration to jointly include both edge nodes and the cloud [90].…”

Section: Discussion and Related Future Workmentioning

confidence: 99%

“…While such technologies were more applicable to cloud services, they are increasingly expanded and implemented at the edge node level. IoT endpoint device security can strongly benefit via joint physical and virtual isolation, and future research need to align relevant research with such IoT architecture patterns [89,90]. Organisations seeking to adopt security-by-design approaches would benefit from methodologies and tools that assist in appropriate prioritisation of any upgrades related to security.…”

Section: Discussion and Related Future Workmentioning

confidence: 99%

See 1 more Smart Citation

A Design Approach to IoT Endpoint Security for Production Machinery Monitoring

Tedeschi

Emmanouilidis

Mehnen

et al. 2019

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT) has significant potential in upgrading legacy production machinery with monitoring capabilities to unlock new capabilities and bring economic benefits. However, the introduction of IoT at the shop floor layer exposes it to additional security risks with potentially significant adverse operational impact. This article addresses such fundamental new risks at their root by introducing a novel endpoint security-by-design approach. The approach is implemented on a widely applicable production-machinery-monitoring application by introducing real-time adaptation features for IoT device security through subsystem isolation and a dedicated lightweight authentication protocol. This paper establishes a novel viewpoint for the understanding of IoT endpoint security risks and relevant mitigation strategies and opens a new space of risk-averse designs that enable IoT benefits, while shielding operational integrity in industrial environments.

show abstract

Section: Discussion and Related Future Workmentioning

confidence: 99%

Section: Discussion and Related Future Workmentioning

confidence: 99%

A Design Approach to IoT Endpoint Security for Production Machinery Monitoring

Tedeschi

Emmanouilidis

Mehnen

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…This leads to a situation where any present security threat will spread and amplify more rapidly called the "speed of ambush" factor and has a more significant impact than in a typical client-server network. It is essential to highlight that, the hosts in a virtualized environment must understand their trust boundaries and responsibilities for each other to secure the whole cloud environment as set by CSPs before moving to the cloud [32,33].…”

Section: The 'Velocity-of-attack'mentioning

confidence: 99%

“…A hypervisor or VMM is installed to execute several guest VMs and applications concurrently on a single host physical server machine and to provide separation amongst the guest VMs in a cloud environment [33]. These hypervisors are vulnerable and prone to attacks from various hackers.…”

Section: Hyperjackingmentioning

confidence: 99%

Next-generation Blockchain-Enabled Virtualized Cloud Security Solutions: Review and Open Challenges

Uddin¹,

Khalique²,

Jumani³

2020

Preprint

View full text Add to dashboard Cite

This paper reviews, discusses, and highlights some of the standard cloud computing vulnerabilities primarily related to virtualization platforms and their implementations while outsourcing services and resources to different end-users and business enterprises. Furthermore, we provide Blockchain-enabled solutions for virtualized cloud computing platform involving both the end-users as well as cloud service providers (CSP) to address and solve different security and privacy-related vulnerabilities using blockchain-enabled solutions to improve their cloud services and resource provisioning facilities.

show abstract

“…Edge computing offers essential services to support this critical concept of Industry 4.0 [22], [23]. The outcomes of the edge computing environment can support the need in the case of inter-connectivity, higher reliability, realtime predictive analysis, and low latency [16], [24], [25]. Specifically, the form of Artificial Intelligence (AI) in edge computing is almost unavoidable.…”

Section: Introductionmentioning

confidence: 99%

iSEC: An Optimized Deep Learning Model for Image Classification on Edge Computing

2020

View full text Add to dashboard Cite

Optimization strategies in deep learning models require different techniques for different use cases. Besides, various phases of the model deployment life-cycle specify possible and particular optimization strategies. In this paper, an optimized deep learning model on the edge computing environment is proposed for image classification cases. For preparing the dataset, the image preprocessing and data augmentation methods are utilized to prepare the data for the training process. To accelerate the deep learning training process, this system implemented CPU optimization and hyperparameter tuning. Tensorflow is applied as a framework for the training model. InceptionV3, VGG16, and MobileNet are applied as topology implemented in the deep learning training comparison. In this case, InceptionV3 was used for modeling the deep learning applications on edge. To optimize the trained model, a Model Optimizer is used on the edge device. It can be seen in the experiments, MobileNet was the least accurate model ( 85%) and the longest time to load the model (71s). VGG16 was the most reliable (91%) and the shortest time to load the model (50s). InceptionV3 has median accuracy (87%) and the average time to load the model (52s).

show abstract

Reprint of : LEGIoT: A Lightweight Edge Gateway for the Internet of Things

Cited by 14 publications

References 30 publications

A Design Approach to IoT Endpoint Security for Production Machinery Monitoring

A Design Approach to IoT Endpoint Security for Production Machinery Monitoring

Next-generation Blockchain-Enabled Virtualized Cloud Security Solutions: Review and Open Challenges

iSEC: An Optimized Deep Learning Model for Image Classification on Edge Computing

Contact Info

Product

Resources

About