Projects per year
Abstract
Machine learning (ML) promises advances in automation and threat detection for the future generations of communication networks. However, new threats are introduced, as adversaries target ML systems with malicious data. Adversarial attacks on tree-based ML models involve crafting input perturbations that exploit non-smooth decision boundaries, causing misclassifications. These so-called evasion attacks are imperceptible, as they do not significantly alter the input data distribution and have been shown to degrade the performance of tree-based models across various tasks. Adversarial training and genetic algorithms have been proposed as potential defenses against these attacks. In this paper, we explore the robustness of tree-based models for network intrusion detection systems. This study evaluates an optimization approach inspired by genetic algorithms to generate adversarial samples and studies the impact of adversarial training on the accuracy of attack detection. This paper exposed random forest and extreme gradient boosting classifiers to various adversarial samples generated from communication network-related CIC-IDS2019 and 5G-NIDD datasets. The results indicate that the improvements of robustness to adversarial attacks come with a cost to the accuracy of the network intrusion detection models. These costs can be optimized with intelligent, use case-specific feature engineering.
Original language | English |
---|---|
Article number | 6 |
Number of pages | 25 |
Journal | Network |
Volume | 5 |
Issue number | 1 |
DOIs | |
Publication status | Published - 17 Feb 2025 |
MoE publication type | A1 Journal article-refereed |
Funding
This work was supported by the AI-NET-ANTILLAS project, partially funded by Business Finland. The work has also been supported by ERCIM.
Keywords
- machine learning
- tree-based models
- trustworthiness
- robustness
Fingerprint
Dive into the research topics of 'GAOR: Genetic Algorithm-Based Optimization for Machine Learning Robustness in Communication Networks'. Together they form a unique fingerprint.Projects
- 1 Finished
-
AI-NET-ANTILLAS: Accellerating digital transformation in Europe by Intelligent NETwork automation - Autonomous end-to-end optimization
Suomalainen, J. (Manager) & Räty, T. (Participant)
1/06/21 → 31/08/24
Project: Business Finland project