Pushing intelligence to the network edge

Salman, Ola; Chaddad, Louma; Elhajj, Imad H.; Chehab, Ali; Kayssi, Ayman

doi:10.1109/sds.2018.8370427

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI-based IDS and traffic classification schemes have been presented in the literature. Recently, a non-cryptographic device authentication scheme was presented in [368,369] and it is based on the network generated traffic. The presented solution uses an intelligent authentication factor ("you are"), that can help in reducing the false positive detection rate (illegal access probability), if combined with another factor(s) ("you know" and "you have").…”

Section: Future Research Directionsmentioning

confidence: 99%

Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations

Yaacoub

Noura

Salman

et al. 2021

Int. J. Inf. Secur.

Self Cite

123

View full text Add to dashboard Cite

The recent digital revolution led robots to become integrated more than ever into different domains such as agricultural, medical, industrial, military, police (law enforcement), and logistics. Robots are devoted to serve, facilitate, and enhance the human life. However, many incidents have been occurring, leading to serious injuries and devastating impacts such as the unnecessary loss of human lives. Unintended accidents will always take place, but the ones caused by malicious attacks represent a very challenging issue. This includes maliciously hijacking and controlling robots and causing serious economic and financial losses. This paper reviews the main security vulnerabilities, threats, risks, and their impacts, and the main security attacks within the robotics domain. In this context, different approaches and recommendations are presented in order to enhance and improve the security level of robotic systems such as multi-factor device/user authentication schemes, in addition to multi-factor cryptographic algorithms. We also review the recently presented security solutions for robotic systems.

show abstract

Section: Future Research Directionsmentioning

confidence: 99%

Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations

Yaacoub

Noura

Salman

et al. 2021

Int. J. Inf. Secur.

Self Cite

123

View full text Add to dashboard Cite

show abstract

“…In our previous work, 2 we present a framework for traffic identification and abnormal traffic detection. This framework consists of three components, a classifier, a security orchestrator, and an intrusion detection module.…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, practically, deploying new traffic control functionalities on top of the traditional network is not a straightforward task, and given the large scale within IoT networks, there is a need for a scalable management solution 1 . To this end, the framework that we propose, which is an extension of our previous work, 2 will extract only simple features per packet for any 16 consecutive packets of a flow to identify the IoT device type and detect attack traffic. The extracted features are the packets' direction, size, timestamp, and transport protocol.…”

Section: Introductionmentioning

confidence: 99%

A machine learning based framework for IoT device identification and abnormal traffic detection

Salman

Elhajj

Chehab

et al. 2019

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

Network security is a key challenge for the deployment of Internet of Things (IoT). New attacks have been developed to exploit the vulnerabilities of IoT devices. Moreover, IoT immense scale will amplify traditional network attacks. Machine learning has been extensively applied for traffic classification and intrusion detection. In this paper, we propose a framework, specifically for IoT devices identification and malicious traffic detection. Pushing the intelligence to the network edge, this framework extracts features per network flow to identify the source, the type of the generated traffic, and to detect network attacks. Different machine learning algorithms are compared with random forest, which gives the best results: Up to 94.5% accuracy for device‐type identification, up to 93.5% accuracy for traffic‐type classification, and up to 97% accuracy for abnormal traffic detection.

show abstract

A review on machine learning–based approaches for Internet traffic classification

et al. 2020

View full text Add to dashboard Cite

Pushing intelligence to the network edge

Cited by 6 publications

References 21 publications

Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations

Robotics cyber security: vulnerabilities, attacks, countermeasures, and recommendations

A machine learning based framework for IoT device identification and abnormal traffic detection

A review on machine learning–based approaches for Internet traffic classification

Contact Info

Product

Resources

About