{"id":7,"date":"2025-02-17T18:30:37","date_gmt":"2025-02-17T18:30:37","guid":{"rendered":"https:\/\/onlineacademiccommunity.uvic.ca\/haydendunstancsc466\/?p=7"},"modified":"2025-02-17T18:30:37","modified_gmt":"2025-02-17T18:30:37","slug":"project-proposal-network-intrusion-detection-with-machine-learning","status":"publish","type":"post","link":"https:\/\/onlineacademiccommunity.uvic.ca\/haydendunstancsc466\/2025\/02\/17\/project-proposal-network-intrusion-detection-with-machine-learning\/","title":{"rendered":"Project Proposal – Network Intrusion Detection with Machine Learning"},"content":{"rendered":"\n

Hayden Dunstan, CSC 466<\/p>\n\n\n\n

Overview<\/h1>\n\n\n\n

As many students in our CSC 446 class discussions have agreed, network security is a top priority as the internet is becoming increasingly popular, and an increasing amount of personal information is being stored in online servers. <\/p>\n\n\n\n

Network intrusion detection is widely accepted as an effective method for dealing with network threats[1], though traditional rule-based IDS systems (like Snort) struggle with new attack patterns. During my project I will investigate the effectiveness of Machine Learning Methods on intrusion detection datasets, and attempt to train a model that can effectively detect advanced threats, in order to gain a better understanding of network attacks, and machine learning.<\/p>\n\n\n\n

Project Plan<\/h1>\n\n\n\n

I plan to use the UNSW-NB15 dataset[2] created by the University of Sydney which contains 9 types of attacks, and 49 features. The set contains over 2 million records, and has conveniently been partitioned into a test set and a training set. <\/p>\n\n\n\n

For the first part of my project, I will design a program that can read pcap files and output their features. In the second part of my project I will train two models,  using Random forests and Neural networks respectively, and then evaluate their performance and show the capabilities of my final model in my final report.<\/p>\n\n\n\n

Schedule Dates<\/h1>\n\n\n\n