Analyzing the Impact of Cyber Security Related Attributes for Intrusion Detection Systems

Abstract

Machine learning (ML) is one of the dominating technologies practiced in both the industrial and academic domains throughout the world. ML algorithms can examine the threats and respond to intrusions and security incidents swiftly in an instinctive way. It plays a critical function in providing a proactive security mechanism in the cybersecurity domain. Cybersecurity ensures the real time protection of information, information systems, and networks from intruders. Several security and privacy reports have cited that there has been a rapid increase in both the frequency and the number of cybersecurity breaches in the last decade. Information security has been compromised by intruders at an alarming rate. Anomaly detection, phishing page identification, software vulnerability diagnosis, malware identification, and denial of services attacks are the main cyber-security issues that demand effective solutions. Researchers and experts have been practicing different approaches to address the current cybersecurity issues and challenges. However, in this research endeavor, our objective is to make an idealness assessment of machine learning-based intrusion detection systems (IDS) under the hesitant fuzzy (HF) conditions, using a multi-criteria decision making (MCDM)-based analytical hierarchy process (AHP) and technique for order of preference by similarity to ideal-solutions (TOPSIS). Hesitant fuzzy sets are useful for addressing decision-making situations in which experts must overcome the reluctance to make a conclusion. The proposed research project would assist the machine learning practitioners and cybersecurity specialists in identifying, selecting, and prioritizing cybersecurity-related attributes for intrusion detection systems, and build more ideal and effective intrusion detection systems.

Evaluating modern intrusion detection methods in the face of Gen V multi-vector attacks with fuzzy AHP-TOPSIS

“…Their outcomes showcased the framework’s efficacy in selecting reliable and secure alternatives among IoMT systems. Alharbi et al [ 22 ] conducted an idealness assessment of machine learning-based IDS under hesitant fuzzy conditions, utilizing AHP and TOPSIS. Their approach assists machine learning practitioners in selecting and prioritizing attributes for intrusion detection systems.…”

Efficiency Evaluation of Cyber Security Based on EBM-DEA Model

“…We use the EBM-I-C, input-oriented under the assumption of constant returns-to-scale in DEA (Alghassab, 2022;Alharbi et al, 2021;Bian & Yang, 2010;Bin Arfaj et al, 2022;Chen et al, 2022;Chen & He, 2017;Chen et al, 2018;Chen et al, 2019), to evaluate the effectiveness of each cybersecurity company. This part's financial data from 2020 is shown in Table 2.…”