An Improved Information Security Risk Assessments Method for Cyber-Physical-Social Computing and Networking

• Published in: IEEE access Vol. 6; pp. 10311 - 10319
• Main Authors: Li, Senyu, Bi, Fangming, Chen, Wei, Miao, Xuzhi, Liu, Jin, Tang, Chaogang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Back propagation; Back propagation networks; BP neural network; cuckoo search algorithm; Evolutionary algorithms; Information security; Information security risk assessment; Integrated circuits; Internet of Things; Neural networks; Organizations; Risk assessment; Risk management; Search algorithms; Security; Security management; Sociology; Standards organizations
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2018.2800664

In virtue of the rapid development of the Internet of Things (IoT), Organizations have grown to rely on their cyber systems and networks. However, this phenomenon also creates many new information security issues. In this paper, we propose an evolutionary algorithm improved cuckoo search (ICS) to pretrain a backpropagation neural network (BPNN) for the sake of improving the accuracy and stability. Using this pre-training process, the BPNN can surmount the defect of falling into the local minima and greatly improve its efficiency. Then, this neural network is used as a part of information security risk assessment (ISRA) processes for a miniature IoT system. An illustration example is introduced to demonstrate that the ICS-BPNN outperforms other neural networks in this ISRA process.