# An Adversarial Approach for Explainable AI in Intrusion Detection Systems

arXiv: https://arxiv.org/abs/1811.11705 · HTML: https://mlsanity.com/paper/1811.11705/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 22 of 22)

- [Explainable Artificial Intelligence Approaches: A Survey](https://mlsanity.com/paper/2101.09429/) (2021)
- [Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2207.06236/) (2022)
- [The Role of Machine Learning in Cybersecurity](https://mlsanity.com/paper/2206.09707/) (2022)
- [SoK: Explainable Machine Learning for Computer Security Applications](https://mlsanity.com/paper/2208.10605/) (2022)
- [Explaining Network Intrusion Detection System Using Explainable AI Framework](https://mlsanity.com/paper/2103.07110/) (2021)
- [XAI for Cybersecurity: State of the Art, Challenges, Open Issues and Future Directions](https://mlsanity.com/paper/2206.03585/) (2022)
- [A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions](https://mlsanity.com/paper/2204.12822/) (2022)
- [TRUST XAI: Model-Agnostic Explanations for AI With a Case Study on IIoT Security](https://mlsanity.com/paper/2205.01232/) (2022)
- [A Survey on Explainable Artificial Intelligence for Cybersecurity](https://mlsanity.com/paper/2303.12942/) (2023)
- [Zero-shot learning approach to adaptive Cybersecurity using Explainable AI](https://mlsanity.com/paper/2106.14647/) (2021)
- [Exploring Adversarial Attacks on Neural Networks: An Explainable Approach](https://mlsanity.com/paper/2303.06032/) (2023)
- [Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions](https://mlsanity.com/paper/2211.01036/) (2022)
- [An Adaptive End-to-End IoT Security Framework Using Explainable AI and LLMs](https://mlsanity.com/paper/2409.13177/) (2024)
- [RX-ADS: Interpretable Anomaly Detection using Adversarial ML for Electric Vehicle CAN data](https://mlsanity.com/paper/2209.02052/) (2022)
- [Explainable Artificial Intelligence and Cybersecurity: A Systematic Literature Review](https://mlsanity.com/paper/2303.01259/) (2023)
- [An Approach To Enhance IoT Security In 6G Networks Through Explainable AI](https://mlsanity.com/paper/2410.05310/) (2024)
- [Tabular Diffusion based Actionable Counterfactual Explanations for Network Intrusion Detection](https://mlsanity.com/paper/2507.17161/) (2025)
- [L-XAIDS: A LIME-based eXplainable AI framework for Intrusion Detection Systems](https://mlsanity.com/paper/2508.17244/) (2025)
- [Towards Explainable Meta-Learning for DDoS Detection](https://mlsanity.com/paper/2204.02255/) (2022)
- [Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems](https://mlsanity.com/paper/2411.09393/) (2024)
- [Spatio-Temporal Attention Graph Neural Network: Explaining Causalities With Attention](https://mlsanity.com/paper/2603.10676/) (2026)
- [Probabilistic Robustness-driven Universal Adversarial Perturbations with Explainability against Deep Reinforcement Learning-based Intrusion Detection System](https://mlsanity.com/paper/2609.30605/) (2026)

## Abstract (arXiv)

Despite the growing popularity of modern machine learning techniques (e.g. Deep Neural Networks) in cyber-security applications, most of these models are perceived as a black-box for the user. Adversarial machine learning offers an approach to increase our understanding of these models. In this paper we present an approach to generate explanations for incorrect classifications made by data-driven Intrusion Detection Systems (IDSs). An adversarial approach is used to find the minimum modifications (of the input features) required to correctly classify a given set of misclassified samples. The magnitude of such modifications is used to visualize the most relevant features that explain the reason for the misclassification. The presented methodology generated satisfactory explanations that describe the reasoning behind the mis-classifications, with descriptions that match expert knowledge. The advantages of the presented methodology are: 1) applicable to any classifier with defined gradients. 2) does not require any modification of the classifier model. 3) can be extended to perform further diagnosis (e.g. vulnerability assessment) and gain further understanding of the system. Experimental evaluation was conducted on the NSL-KDD99 benchmark dataset using Linear and Multilayer perceptron classifiers. The results are shown using intuitive visualizations in order to improve the interpretability of the results.