DYNAMITE: Dynamic Defense Selection for Enhancing Machine Learning-based Intrusion Detection Against Adversarial Attacks
Year: 2025
Type: preprint
Abstract: The rapid proliferation of the Internet of Things (IoT) has introduced substantial security vulnerabilities, highlighting the need for robust Intrusion Detection Systems (IDS). Machine learning-based intrusion detection systems (ML-IDS) have significantly improved threat detection capabilities; however, they remain highly susceptible to adversarial attacks. While numerous defense mechanisms have been proposed to enhance ML-IDS resilience, a systematic approach for selecting the most effective defense against a specific adversarial attack remains absent. To address this challenge, we propose Dynamite, a dynamic defense selection framework that enhances ML-IDS by intelligently identifying and deploying the most suitable defense using a machine learning-driven selection mechanism. Our results demonstrate that Dynamite achieves a 96.2% reduction in computational time compared to the Oracle, significantly decreasing computational overhead while preserving strong prediction performance. Dynamite also demonstrates an average F1-score improvement of 76.7% over random defense and 65.8% over the best static state-of-the-art defense.
Source: arXiv (Cornell University)
Authors: Chen, Jing, Gungor, Onat, Shang, Zhengli, Li, Elvin, Rosing, Tajana
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979299550
Cites:
Cited by:
Related to: