Secure IoT edge: Threat situation awareness based on network traffic

Zhao, Yuyu; Cheng, Guang; Duan, Yu; Gu, Zhouchao; Zhou, Yuyang; Tang, Lu

doi:10.1016/j.comnet.2021.108525

Cited by 8 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further evaluated the prediction performance of dynamic defense and compared it with TSA-AdaBoost [ 49 ], a situation awareness algorithm based on the AdaBoost machine learning method. DDESS adopts the batch normalization [ 40 ] to reduce the influence of gradient vanishing problem, and max-pooling layer and

convolutional kernel [ 41 ] for dimensionality reduction.…”

Section: Methodsmentioning

confidence: 99%

Towards Double Defense Network Security Based on Multi-Identifier Network Architecture

Wang

Smahi

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Recently, more and more mobile devices have been connected to the Internet. The Internet environment is complicated, and network security incidents emerge endlessly. Traditional blocking and killing passive defense measures cannot fundamentally meet the network security requirements. Inspired by the heuristic establishment of multiple lines of defense in immunology, we designed and prototyped a Double Defense strategy with Endogenous Safety and Security (DDESS) based on multi-identifier network (MIN) architecture. DDESS adopts the idea of a zero-trust network, with identity authentication as the core for access control, which solves security problems of traditional IP networks. In addition, DDESS achieves individual static security defense through encryption and decryption, consortium blockchain, trusted computing whitelist, and remote attestation strategies. At the same time, with the dynamic collection of data traffic and access logs, as well as the understanding and prediction of the situation, DDESS can realize the situation awareness of network security and the cultivation of immune vaccines against unknown network attacks, thus achieving the active herd defense of network security.

show abstract

convolutional kernel [ 41 ] for dimensionality reduction.…”

Section: Methodsmentioning

confidence: 99%