Detection Algorithm of Abnormal Behavior in Security for IIoT Based on Random Inspection

Traditional security abnormal behavior detection algorithms are difficult to adapt to the Industrial Internet of Things scenario. To this end, an algorithm for detecting abnormal behaviors of the Industrial Internet of Things based on random inspections is proposed. Based on the clustered hierarchical Industrial Internet of Things topology, it manages the number of network nodes and sets different inspection inspection rates according to the reputation value interval. Detect and analyze the communication behavior attributes of nodes in the network such as packet loss rate and transmission delay, perform reputation evaluation, and then discover abnormal behaviors of the nodes and detect different types of malicious attacks. Simulation results show that the new abnormal behavior detection algorithm improves the detection accuracy without affecting the life of the network. The proposed random inspection mechanism helps the algorithm to find malicious nodes with low energy consumption and high efficiency, and improves the security of the Industrial Internet of Things.

Keywords

Industrial Internet of Things ； Malicious node ； Abnormal behavior ； Random inspection ； Reputation evaluation

References

Oh SH, Hong CO, Choi YA. A malicious and malfunctioning node detection scheme for wireless sensor networks[J]. Wireless Sensor Network, 2012, 4(3): 84-90.

Babu Shaik Sahil, Raha Arnab, Naskar Mrinal Kanti. Trust evaluation based on node's characteristics and neighbouring nodes' recommendations for WSN[J]. Wireless Sensor Network, 2014, 6(8): 157-172.

L. Bhasker. Genetically derived secure cluster-based data aggregation in wireless sensor networks[J]. IET Information Security, 2014, 8(1): 1-7.

Y. Liu, M. Dong, K. Ota and A. Liu. ActiveTrust: Secure and Trustable Routing in Wireless Sensor Networks. IEEE Transactions on Information Forensics and Security, 2016, 11(9): 2013-2027.

OUYANG X, TIAN B, LI D. A novel hierarchical reputation model for wireless sensor networks[J]. International journal of digital content technology and its applications, 2012, 6(10): 61-69.

Read-around

陳則宏、陳羿霖、張維晏、蔡崇煒（2019）。A Hybrid Classification Algorithm for Intrusion Detection System。資訊安全通訊，25(1)，14-27。https://www.airitilibrary.com/Article/Detail?DocID=a0000270-201902-201903150006-201903150006-14-27
Xue, Y. (2022). Research on Network Security Intrusion Detection with an Extreme Learning Machine Algorithm. International Journal of Network Security, 24(1), 29-35. https://doi.org/10.6633/IJNS.202201_24(1).04
Zhang, Z. H., Shen, H., & Sang, Y. P. (2007). An Observation-Centric Analysis on the Modeling of Anomaly-based Intrusion Detection. International Journal of Network Security, 4(3), 292-305. https://doi.org/10.6633/IJNS.200705.4(3).08
Dong, R. H., Wu, D. F., Zhang, Q. Y., & Duan, H. X. (2018). Mutual Information-based Intrusion Detection Model for Industrial Internet. International Journal of Network Security, 20(1), 131-140. https://doi.org/10.6633/IJNS.201801.20(1).14
林福陞（2020）。A Study of Intrusion Detection System Based on Genetic Algorithm for Abnormal Flow Detection〔碩士論文，國立臺中科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0061-2101202009483700

Altmetrics

Detection Algorithm of Abnormal Behavior in Security for IIoT Based on Random Inspection

Download

Read this ↓