# An Adversarial Robustness Benchmark for Enterprise Network Intrusion Detection

arXiv: https://arxiv.org/abs/2402.16912 · HTML: https://mlsanity.com/paper/2402.16912/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 25 Feb 2024.

## Builds on (most cited first, 7 of 7)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection](https://mlsanity.com/paper/2203.04234/) (2022)
- [A Comparative Analysis of Machine Learning Techniques for IoT Intrusion Detection](https://mlsanity.com/paper/2111.13149/) (2021)
- [Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification](https://mlsanity.com/paper/2301.13122/) (2023)
- [SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detection](https://mlsanity.com/paper/2308.06819/) (2023)
- [Constrained Adversarial Learning for Automated Software Testing: a literature review](https://mlsanity.com/paper/2303.07546/) (2023)

## Built on by (most cited first, 3 of 3)

- [Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection](https://mlsanity.com/paper/2404.04188/) (2024)
- [Efficient Network Traffic Feature Sets for IoT Intrusion Detection](https://mlsanity.com/paper/2406.08042/) (2024)
- [Flow Exporter Impact on Intelligent Intrusion Detection Systems](https://mlsanity.com/paper/2412.14021/) (2024)

## Abstract (arXiv)

As cyber-attacks become more sophisticated, improving the robustness of Machine Learning (ML) models must be a priority for enterprises of all sizes. To reliably compare the robustness of different ML models for cyber-attack detection in enterprise computer networks, they must be evaluated in standardized conditions. This work presents a methodical adversarial robustness benchmark of multiple decision tree ensembles with constrained adversarial examples generated from standard datasets. The robustness of regularly and adversarially trained RF, XGB, LGBM, and EBM models was evaluated on the original CICIDS2017 dataset, a corrected version of it designated as NewCICIDS, and the HIKARI dataset, which contains more recent network traffic. NewCICIDS led to models with a better performance, especially XGB and EBM, but RF and LGBM were less robust against the more recent cyber-attacks of HIKARI. Overall, the robustness of the models to adversarial cyber-attack examples was improved without their generalization to regular traffic being affected, enabling a reliable detection of suspicious activity without costly increases of false alarms.