Abstract
Rapid shifting by government sectors and companies to provide their services and products over the internet, has immensely increased internet usage by individuals. Through extranets to network services or corporate networks used for personal purposes, computer hackers can lead to financial losses and manpower/time consumption. Therefore, it is vital to take all necessary measures to minimize losses by detecting attacks preemptively. Due to learning algorithms in cyberspace security challenges, deep learning-based cyber defense has lately become a hot topic. Penetration testing, malware categorization and identification, spam filtering, and spoofing detection are just a few of the key concerns in cyber defense that were tackled using Machine Learning (ML) approaches (Somme, 2020). Result, effective adaptive approaches, such as machine learning approaches could result in increased response times, reduced probability of false alerts, as well as cheaper computing and communication expenses. Our primary point is to demonstrate that the problem of detecting malware is distinct from other technologies, making it far more difficult for the access control group to properly use machine learning.
Publication Date
12-2022
Document Type
Master's Project
Student Type
Graduate
Degree Name
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research (Dubai)
Advisor
Sanjay Modak
Advisor/Committee Member
Hammou Messatfa
Recommended Citation
Almulla, Khalid, "Cyber-attack detection in network traffic using machine learning" (2022). Thesis. Rochester Institute of Technology. Accessed from
https://repository.rit.edu/theses/11320
Campus
RIT Dubai
