Title

NETWORK ATTACK CLASSIFICATION WITH FEW-SHOT LEARNING METHODS

Abstract

Abstract

As the number of devices using the Internet increases, the network attacks that these devices are exposed to also diversify. Classifying the network attack type from the network packets is important to prevent the damage of the attack and to minimize it in cases where it cannot be prevented. Classical machine learning methods and deep learning methods need a lot of data to get successful results. Unfortunately, preparing and labeling large amounts of data is costly in today’s conditions. This cost is mostly due to the training of the experts who will do the labeling process, the difficulty of generating attack environments, and the complexity of the attack. This study examines the problem of classifying network attacks with limited data without using a few data in the learning process by applying few-shot learning methods. To investigate the problem, we generate three different datasets using previously labeled large datasets such as CIC-IDS2017 and UNSW-NB15. We apply three promising approaches, where two of them are based on Prototypical Networks, and one of them is based on Relation Networks.

Supervisor(s)

Supervisor(s)

ISMAIL TUZUN

Date and Location

Date and Location

2022-09-14 13:30:00

Category

Category

MSc_Thesis