Utilizing Graph Neural Networks for Robust DDoS Attack Detection in Network Security 2024

Presenter: Kartikeya Sharma
Room: Ballroom, EMU 244, Level 2
Presentation: Utilizing Graph Neural Networks for Robust DDoS Attack Detection in Network Security 
Time: 03:30p – 04:00p     

In this talk, we will explore the application of Graph Neural Networks (GNNs) in detecting Distributed Denial of Service (DDoS) attacks. We will introduce GNNs, compare them with traditional neural networks, and highlight their evolution and adoption. We will also compare traditional detection methods with AI-based approaches and how GNN based approaches can be advantageous. Finally, we will talk about two important GNN models used in DDoS detection and discuss their superior performance compared to traditional machine learning models.

My presentation is about the detection of the real-world cyber-attacks using AI. It aligns well with the Cyber-Technical track as it provides technical insights into real-world attacks, shows the potential of AI and machine learning in cyber-attack detection, and transfers knowledge about noble machine learning detection models to IT and security professionals.