Integrated Fuzzy Based Computational Mechanism for the Selection of Effective Malicious Traffic Detection Approach

Abstract

A mechanism to effectively detect malicious traffic in the present context where new cyber criminals and threatening actors are emerging every day, has become a compelling need. These invaders use overwhelming tactics that mask the nature of attacks and make bad acts seem innocuous. A growing number of trustworthy electronic systems and facilities have been introduced with the fast development of pervasive digital technologies. However threats to cyber-security continue to grow, posing hindrance in the efficient use of digital services. The detection and classification of malicious traffic due to security threats can be done by an efficacious traffic detection approach. The development of a smart, precise malicious traffic detection system has therefore become a subject of extensive research. Current traffic detection systems are typically employed in conventional network traffic detection. These systems sometimes face failure and cannot recognize many known or modern security threats. This is because they rely on conventional algorithms which focus less on precise selection and classification of functions. As a result, several well-known traffic signatures remain unidentified and latent. Hence, there is a need to evaluate each significant malicious traffic detection system based on the performance of the system. In this research work, the author has used the Fuzzy AHP methodology which is designed to address the issues related to the vagueness, uncertainties and total awareness of languages. In addition, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) was implemented in order to assess the order of preference. Furthermore, the Multi-Criteria Decision-Making (MCDM) method was used for classifying the impact of the alternatives according to their overall performance. The study’s conclusive evaluations will be a corroborative reference for the practitioners working in the domain of assessing and selecting the most effective traffic detection approach for more reliable, efficient and systematic design.