Using Deep Learning in Detecting Network Attacks

Date

2024-6

Author

Vahi, Arsalan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

78
views

28
downloads

Cite This

Deep learning significantly enhances network attack detection by identifying and analyzing patterns and anomalies in network traffic. Traditional network security methods fail to recognize evolving threats; On the other hand, deep learning models can detect such threats. The important characteristics of these models are their ability to learn from data continuously, improve detection accuracy, and adapt to new attack vectors. However, the main disadvantage is the challenges of implementing network security. These challenges include the need for substantial computational resources and expertise. Despite these hurdles, deep learning provides a powerful and dynamic approach to network security, offering real-time threat detection and significantly bolstering cybersecurity defenses. In this document, we propose an idea of using image channels to find abnormal patterns in network traffic. We implemented this idea in a deep learning architecture and evaluated

Subject Keywords

Deep Learning,, Network Attacks, DNS Spoofing Attacks, Anomaly Detection

URI

https://hdl.handle.net/11511/113009

Collections

Graduate School of Informatics, Term Project