Redefining DDoS Attack Detection Using A Dual-Space Prototypical Network-Based Approach

TL;DR

This paper introduces a dual-space prototypical network that improves DDoS attack detection accuracy by leveraging geometric and angular similarity measures, demonstrating robustness across various training environments.

Contribution

The paper presents a novel dual-space prototypical network with a unique loss function for enhanced DDoS detection, advancing deep learning methods in cybersecurity.

Findings

Achieves 94.85% accuracy and 94.71% F1-Score with reduced training data

Demonstrates robustness across offline, online, and prototypical scenarios

Enhances detection sensitivity for diverse attack patterns

Abstract

Distributed Denial of Service (DDoS) attacks pose an increasingly substantial cybersecurity threat to organizations across the globe. In this paper, we introduce a new deep learning-based technique for detecting DDoS attacks, a paramount cybersecurity challenge with evolving complexity and scale. Specifically, we propose a new dual-space prototypical network that leverages a unique dual-space loss function to enhance detection accuracy for various attack patterns through geometric and angular similarity measures. This approach capitalizes on the strengths of representation learning within the latent space (a lower-dimensional representation of data that captures complex patterns for machine learning analysis), improving the model's adaptability and sensitivity towards varying DDoS attack vectors. Our comprehensive evaluation spans multiple training environments, including offline training, simulated online training, and prototypical network scenarios, to validate the model's robustness under diverse data abundance and scarcity conditions. The Multilayer Perceptron (MLP) with Attention, trained with our dual-space prototypical design over a reduced training set, achieves an average accuracy of 94.85% and an F1-Score of 94.71% across our tests, showcasing its effectiveness in dynamic and constrained real-world scenarios.