.png){kind=icon}
Return
Deep-Learning-Based Blockchain for Secure Zero Touch Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/MCOM.001.2200294.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The recent technological advancements in wireless communication systems and the Internet of Things (IoT) have accelerated the development of zero touch networks (ZTNs). ZTNs provide self-monitoring, self-configuring, and automated service-level policies that cannot be fulfilled by the traditional network management and orchestration approaches. Despite the hype, the majority of data exchange between participating entities occurs over insecure public channels, which present a number of possible security risks and attacks. Toward this end, we first analyze the attack surface on IoT-enabled ZTNs and the inherent architectural flaws for such threats. After an overview of attack surface, this article presents a new deep-learning- and blockchain-assisted case study for secure data sharing in ZTNs. Specifically, first, we design a novel variational autoencoder (VAE) and attention-based gated recurrent units (AGRU)-based intrusion detection system (IDS) for ZTNs. Second, a novel authentication protocol that combines blockchain, smart contracts (SCs), elliptic curve cryptography (ECC), and a proof of authority (PoA) consensus mechanism is developed to improve secure data sharing in ZTNs. The extensive experimental results show the effectiveness of the proposed approach. Lastly, this work discusses critical issues, opportunities, and open research directions to solve these challenges.
Keywords:
Blockchains
Servers
Security
Internet of Things
Feature extraction
Deep learning
Logic gates
Journal
IF:
8.2
Papers:
6.9K
Citations:
2.2W
Organization
View more organizations
Cited Papers
.png){kind=icon}
ShareSave
ShareSave
ShareSave View more