Network Security Incidents Frequency Prediction Based on Improved Genetic Algorithm and LSSVM

Since the frequency of network security incidents is nonlinear,traditional prediction methods such as ARMA,Gray systems are difficult to deal with the problem.When the size of sample is small,methods based on artificial neural network may not reach a high degree of preciseness.Least Squares Support Vector Machines (LSSVM) is a kind of machine learning methods based on the statistics learning theory,it can be applied to solve small sample and non-linear problems very well.This paper applied LSSVM to predict the occur frequency of network security incidents.To improve the accuracy,it used an improved genetic algorithm to optimize the parameters of LSSVM.Verified by real data sets,the improved genetic algorithm (IGA) converges faster than the simple genetic algorithm (SGA),and has a higher efficiency in the optimization procedure.Specially,the optimized LSSVM model worked very well on the prediction of frequency of network security incidents.

Knowledge Management Strategy for Handling Cyber Attacks in E-Commerce with Computer Security Incident Response Team (CSIRT)

Electronic Commerce (E-Commerce) was created to help expand the market share network through the internet without the boundaries of space and time. However, behind all the benefits obtained, E-Commerce also raises the issue of consumer concerns about the responsibility for personal data that has been recorded and collected by E-Commerce companies. The personal data is in the form of consumer identity names, passwords, debit and credit card numbers, conversations in email, as well as information related to consumer requests. In Indonesia, cyber attacks have occurred several times against 3 major E-Commerce companies in Indonesia. In 2019, users’ personal data in the form of email addresses, telephone numbers, and residential addresses were sold on the deep web at Bukalapak and Tokopedia. Even though E-Commerce affected by the cyber attack already has a Computer Security Incident Response Team (CSIRT) by recruiting various security engineers, both defense and attack, this system still has a weakness, namely that the CSIRT operates in the aspect of handling and experimenting with defense, not yet on how to store data and prepare for forensics. CSIRT will do the same thing again, and so on. This is called an iterative procedure, one day the attack will come back and only be done with technical handling. Previous research has succeeded in revealing that organizations that have Knowledge Management (KM), the organization has succeeded in reducing costs up to four times from the original without using KM in the cyber security operations. The author provides a solution to create a knowledge management strategy for handling cyber incidents in CSIRT E-Commerce in Indonesia. This research resulted in 4 KM Processes and 2 KM Enablers which were then translated into concrete actions. The KM Processes are Knowledge Creation, Knowledge Storing, Knowledge Sharing, and Knowledge Utilizing. While the KM Enabler is Technology Infrastructure and People Competency.