Date of Graduation

5-2021

Document Type

Thesis

Degree Name

Bachelor of Science

Degree Level

Undergraduate

Department

Computer Science and Computer Engineering

Advisor/Mentor

Zhan, Justin

Committee Member/Reader

Patitz, Matthew

Committee Member/Second Reader

Thompson, Dale R.

Abstract

Due to a rapid increase in network traffic, it is growing more imperative to have systems that detect attacks that are both known and unknown to networks. Anomaly-based detection methods utilize deep learning techniques, including semi-supervised learning, in order to effectively detect these attacks. Semi-supervision is advantageous as it doesn't fully depend on the labelling of network traffic data points, which may be a daunting task especially considering the amount of traffic data collected. Even though deep learning models such as the convolutional neural network have been integrated into a number of proposed network intrusion detection systems in recent years, little work has been done on spatial-temporal feature extraction for network intrusion anomaly detection using semi-supervised learning. This paper introduces Anomaly-CNVAE, a variational autoencoder where the encoding and decoding layers perform convolution and transpose convolution, respectively, in order to account for spatial feature extraction. In addition, in order to account for time-based features in the dataset, the proposed model utilizes 1D-CNN for the convolution operations. The performance of the model in network intrusion detection is evaluated against an autoencoder and a vanilla variational autoencoder. Results show that Anomaly-CNVAE significantly outperforms the other semi-supervised learning models with a 5-10 percent increase in evaluation metrics.

Keywords

Network Intrusion Detection; Semi-Supervised Learning; Anomaly Detection; Service Learning

Download

Share

COinS