Deep Learning for Detection of Routing Attacks in the Internet of Things

Abstract

Cyber threats are a showstopper for Internet of Things (IoT) has recently been used at an industrial scale. Network layer attacks on IoT can cause significant disruptions and loss of information. Among such attacks, routing attacks are especially hard to defend against because of the ad-hoc nature of IoT systems and resource constraints of IoT devices. Hence, an efficient approach for detecting and predicting IoT attacks is needed. Systems confidentiality, integrity and availability depends on continuous security and robustness against routing attacks. We propose a deep-learning based machine learning method for detection of routing attacks for IoT. In our study, the Cooja IoT simulator has been utilized for generation of high-fidelity attack data, within IoT networks ranging from 10 to 1000 nodes. We propose a highly scalable, deep-learning based attack detection methodology for detection of IoT routing attacks which are decreased rank, hello-flood and version number modification attacks, with high accuracy and precision. Application of deep learning for cyber-security in IoT requires the availability of substantial IoT attack data and we believe that the IoT attack dataset produced in this work can be utilized for further research.

Multi-level trust-based intelligence schema for securing of internet of things (IoT) against security threats using cryptographic authentication

“…A deep-learning established machine learning method has been presented in [14] for the IoT to detect the routing attacks. The Cooja IoT emulator has been employed to generate high-fidelity attack data within IoT networks having 10 to 1000 nodes.…”

A Comprehensive Tutorial and Survey of Applications of Deep Learning for Cyber Security

“…It also increases the accuracy of the model to 98.59% which is better than other state-of-the-art models. In [506], a DNN based scalable routing attack detection framework is proposed where the attack dataset is extracted from the Cooja IoT simulator. The proposed framework preprocess the extracted simulator data and selects the useful features which is fed into DNN model as input.…”

Detection and Prevention of Black Hole Attack in RPL Protocol Based on the Threshold Value of Nodes in the Internet of Things Networks

“…In this paper [16] authors has analyzed the behavior of the routing attacks like black-hole, clone attack, civil, sinkhole attack, and selective forwarding attacks and concluded that due to this attack the network may damage in terms of network throughput the experimental results was shown by using the netsim2. In this paper [17] proposed an deep learning approach to detect the routing attacks in the internet of things to simulating the proposed system contiki cooja to simulator was used. Here the proposed system will detect the routing attacks like hello flood, version number modification attack and decreased rank attack.…”