Risk Prediction and Management for Effective Cyber Security Using Weighted Fuzzy C Means Clustering

Abstract

The necessity of the continuous risk assessment as well as management is attracting the people due to the requirement of protecting the risk. The management of the risk plays a significant part in solving the cyber threats within Cyber-Physical System (CPS). However, because of the enhanced complexity of CPS, the cyber-attacks are the most urbane as well as low predictable, which made the risk management tasks more challenging. This research proposes the efficient Cyber Security Risk Management (CSRM) repetition by the utilization of the Weighted Fuzzy C Means (WFCM) clustering for the prediction and management of the cyber risk. Initially, VCDB dataset is collected to estimate the effectiveness of the model and Term Frequency-Inverse Document Frequency (TF-IDF) approach is utilized for the extraction of feature from the collected data. Then, feature selection is performed by using Principal Component Analysis (PCA) and prediction is performed by the utilization of the WFCM. The effectiveness of the WFCM is estimated by using various performance metrices and it achieves the accuracy of 84.2% and precision of 0.746 when compared to the existing methods such as fuzzy and DeepSpamPhisNet (DSPN).