2023 - Full Presentation Schedule

Machine Learning Techniques and their Effects on Cybersecurity Adoptions for Risk Mitigation

Presenter Information

Richmond AdebiayeFollow

Start Date

31-3-2023 2:00 PM

End Date

31-3-2023 2:15 PM

Location

CASB 103 - Physical, Computer, and Chemical Science

Document Type

Presentation

Abstract

Cyberspace has developed into a component that cannot be ignored in any aspect of the modern world. The internet known also as ‘Cyber’ plays an increasingly important role in people's lives all over the world. The growing reliance on the internet and the expanding cyberspace have also increased exposure to potentially harmful threats.

As a result of the proliferation of cybersecurity threats, cybersecurity has evolved into the single most important factor in the cyber world in the fight against all forms of cybercrime, including attacks and fraud. The ever-expanding cyberspace is extremely vulnerable to the ever-increasing possibility of being attacked by an endless variety of online dangers. To ascertain the developments made in detection methods for potential cybersecurity risks and their mitigations, the purpose of this study is to provide a concise review of the various machine learning (ML) techniques that are implemented for cyber fraud detection, spam and malware detection, and vulnerability and penetration risks to networks.

Detection of fraud, intrusion, spam, and malware are among the primary methods used to assess potential cybersecurity risks. In this review paper, we build upon the previous research that has been published. We examine the applications of machine learning (ML) models in cybersecurity and provide a comprehensive review of ML. To the best of our knowledge, this is the first attempt that has been made to compare the time complexity of various machine learning models that are frequently utilized in cybersecurity.

We have conducted a comprehensive analysis to evaluate the performance of each classifier’s performance based on commonly used datasets and various types of cyber threats in addition to commonly deployed security datasets. This study also offers a condensed introduction to various machine learning models and investigates the challenges and limits of applying machine learning techniques to cybersecurity for risk mitigations.

Keywords: cybersecurity; machine learning; malware detection; intrusion detection system; spam classification

This document is currently not available here.

Share

COinS
 
Mar 31st, 2:00 PM Mar 31st, 2:15 PM

Machine Learning Techniques and their Effects on Cybersecurity Adoptions for Risk Mitigation

CASB 103 - Physical, Computer, and Chemical Science

Cyberspace has developed into a component that cannot be ignored in any aspect of the modern world. The internet known also as ‘Cyber’ plays an increasingly important role in people's lives all over the world. The growing reliance on the internet and the expanding cyberspace have also increased exposure to potentially harmful threats.

As a result of the proliferation of cybersecurity threats, cybersecurity has evolved into the single most important factor in the cyber world in the fight against all forms of cybercrime, including attacks and fraud. The ever-expanding cyberspace is extremely vulnerable to the ever-increasing possibility of being attacked by an endless variety of online dangers. To ascertain the developments made in detection methods for potential cybersecurity risks and their mitigations, the purpose of this study is to provide a concise review of the various machine learning (ML) techniques that are implemented for cyber fraud detection, spam and malware detection, and vulnerability and penetration risks to networks.

Detection of fraud, intrusion, spam, and malware are among the primary methods used to assess potential cybersecurity risks. In this review paper, we build upon the previous research that has been published. We examine the applications of machine learning (ML) models in cybersecurity and provide a comprehensive review of ML. To the best of our knowledge, this is the first attempt that has been made to compare the time complexity of various machine learning models that are frequently utilized in cybersecurity.

We have conducted a comprehensive analysis to evaluate the performance of each classifier’s performance based on commonly used datasets and various types of cyber threats in addition to commonly deployed security datasets. This study also offers a condensed introduction to various machine learning models and investigates the challenges and limits of applying machine learning techniques to cybersecurity for risk mitigations.

Keywords: cybersecurity; machine learning; malware detection; intrusion detection system; spam classification