Files and links (1)
Sayed_Abualia_WSU_Thesis572.92 kB
Embargoed Access, Embargo ends: 03/19/2027
Thesis
DDoS Detection in IoT Environments Using an Enhanced Negative Selection Algorithm
Washington State University
Master of Science (MS), Washington State University
12/2024
DOI:
https://doi.org/10.7273/000007235
Abstract
Securing networks against Distributed Denial of Service (DDoS) attacks is a major challenge due to the nature and complexity of these threats. DDoS attacks aim to disrupt network services and can be launched against any organization. Due to their distributed nature, DDoS attacks are particularly challenging to detect. Mitigating these attacks requires sophisticated strategies. It has been demonstrated that bio-inspired methods have the potential to detect DDoS attacks. For example, various Artificial Immune System (AIS) schemes, derived from the human immune system systems, have been successfully used to detect anomalies in network traffic. In this paper, we propose a Gradient boost regression and Adam optimized Negative Selection Algorithm (GANSA) to overcome the difficulties of DDoS detection in the Internet of Things (IoT). Given the dynamic nature of network traffic, we demonstrate that the proposed system accurately detects both known and unknown DDoS attacks because of it is the ability to adjust to changes in network traffic patterns. We evaluate the proposed system against various state-of-the-art machine learning algorithms (e.g., CNN, SVM). We show that the proposed GANSA intrusion detection system can adapt to incoming network traffic in real time while achieving a low false positive rate (0.0003), and near-perfect detection accuracy (0.99), F1 score (0.99), and MCC (0.97).
Metrics
4 Record Views
Details
- Title
- DDoS Detection in IoT Environments Using an Enhanced Negative Selection Algorithm
- Creators
- Sayed Abualia
- Contributors
- Anna Wisniewska (Chair)Scott Wallace (Committee Member)Xuechen Zhang (Committee Member)
- Awarding Institution
- Washington State University
- Academic Unit
- School of Engineering and Computer Science (VANC)
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University
- Number of pages
- 56
- Identifiers
- 99901195539001842
- Language
- English
- Resource Type
- Thesis