A Survey on Explainable Artificial Intelligence for Internet Traffic Classification and Prediction, and Intrusion Detection

A Nascita, G Aceto, D Ciuonzo… - … Surveys & Tutorials, 2024 - ieeexplore.ieee.org
With the increasing complexity and scale of modern networks, the demand for transparent
and interpretable Artificial Intelligence (AI) models has surged. This survey comprehensively …

When adversarial perturbations meet concept drift: an exploratory analysis on ml-nids

G Apruzzese, A Fass, F Pierazzi - Proceedings of the 2024 Workshop on …, 2024 - dl.acm.org
We scrutinize the effects of" blind''adversarial perturbations against machine learning (ML)-
based network intrusion detection systems (NIDS) affected by concept drift. There may be …

Evaluating The Explainability of State-of-the-Art Machine Learning-based Online Network Intrusion Detection Systems

A Kumar, VLL Thing - arxiv preprint arxiv:2408.14040, 2024 - arxiv.org
Network Intrusion Detection Systems (NIDSs) which use machine learning (ML) models
achieve high detection performance and accuracy while avoiding dependence on fixed …

The Missing Link in Network Intrusion Detection: Taking AI/ML Research Efforts to Users

K Dietz, M Mühlhauser, J Kögel, S Schwinger… - IEEE …, 2024 - ieeexplore.ieee.org
Intrusion Detection Systems (IDS) tackle the challenging task of detecting network attacks as
fast as possible. As this is getting more complex in modern enterprise networks, Artificial …

An Empirical Study on Learning Models and Data Augmentation for IoT Anomaly Detection

AT Khorasgani, P Shirani… - 2024 IEEE Conference …, 2024 - ieeexplore.ieee.org
Among many other security applications, anomaly detection is one of the biggest users of
deep learning methods. This growing popularity is mainly driven by two common beliefs:(i) …

ExpIDS: A Drift-Adaptable Network Intrusion Detection System with Improved Explainability

A Kumar, KW Fok, VLL Thing - 2024 34th International …, 2024 - ieeexplore.ieee.org
Despite all the advantages associated with Network Intrusion Detection Systems (NIDSs)
that utilize machine learning (ML) models, there is a significant reluctance among cyber …

[PDF][PDF] The Missing Link in Network Intrusion Detection: Taking AI/ML Research Efforts to Users

J KÖGEL, S SCHWINGER, M SICHERMANN - 2024 - opus.bibliothek.uni-augsburg.de
ABSTRACT Intrusion Detection Systems (IDS) tackle the challenging task of detecting
network attacks as fast as possible. As this is getting more complex in modern enterprise …