Platform Design and Implementation for Flexible Data Processing and Building ML Models of IDS Alerts

Shin, Ik‐Soo; Choi, Youngjoon; Kwon, Taewoong; Lee, Hyeak-Ro; Song, Jungsuk

doi:10.1109/asiajcis.2019.000-4

Cited by 3 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep Learning Model classifier is a type of artificial intelligence that uses deep learning algorithms to classify data into different categories, it is used in applications such as image recognition, text classification, IDS and natural language processing (Shin, 2019). Deep Learning Model classifier with NIDS is a powerful tool to identify and classify malicious activities on a network, it uses deep learning algorithms to detect anomalies in the network traffic and identify suspicious activities, this technology can be used to detect malicious activities like DDoS attacks, malware, and phishing attacks, the Deep Learning Model classifier with NIDS can also be used for anomaly detection, intrusion detection, and threat intelligence, with its advanced capabilities, it can help organizations protect their networks from cyber threats (Kiran, 2022).…”

Section: Model Classifiermentioning

confidence: 99%

A New Software Defined Networks (SDN) in IoTs Based Deep Learning Techniques

BALIK,

AL-HWAIDI

2023

A-JESA

View full text Add to dashboard Cite

In this study, a new software defined networks (SDN) in IoTs based on deep learning techniques was implemented using various types of classifiers such as DNN, CNN, GRU, LSTM RNN and SDN Ryu controller. The system was able to handle high-dimensional and complex data by using NSL-KDD dataset, and was able to detect unknown intrusions that traditional methods may miss. The effectiveness of the proposed model was evaluated by accuracy, precision, recall, F-score, and confusion matrix. Python 3.10 has been used to implementation our system. The proposed system was able to achieve good performance, however, the system's efficacy will be determined by the kind of the data feed and the scale of the issue that is attemped to address. This study highlights the potential of DL-based NIDS with SDN and IoT to detect network intrusions, but also highlights the need for continuous monitoring and updating to ensure that the system remains effective.

show abstract

Section: Model Classifiermentioning

confidence: 99%

A New Software Defined Networks (SDN) in IoTs Based Deep Learning Techniques

BALIK,

AL-HWAIDI

2023

A-JESA

View full text Add to dashboard Cite

show abstract

“…According to Haripriya et al [20], the main objective of applying machine learning algorithms in an IDS focuses on obtaining a low false alarm rate and a high detection rate. As highlighted in [21], using machine learning techniques in an IDS can reduce the occurrence of false positives. The authors also pointed out that one or more models should be used to increase the performance of their detection.…”

Section: Related Workmentioning

confidence: 99%

A Vote-Based Architecture to Generate Classified Datasets and Improve Performance of Intrusion Detection Systems Based on Supervised Learning

Malta

Pinto

2022

Future Internet

View full text Add to dashboard Cite

An intrusion detection system (IDS) is an important tool to prevent potential threats to systems and data. Anomaly-based IDSs may deploy machine learning algorithms to classify events either as normal or anomalous and trigger the adequate response. When using supervised learning, these algorithms require classified, rich, and recent datasets. Thus, to foster the performance of these machine learning models, datasets can be generated from different sources in a collaborative approach, and trained with multiple algorithms. This paper proposes a vote-based architecture to generate classified datasets and improve the performance of supervised learning-based IDSs. On a regular basis, multiple IDSs in different locations send their logs to a central system that combines and classifies them using different machine learning models and a majority vote system. Then, it generates a new and classified dataset, which is trained to obtain the best updated model to be integrated into the IDS of the companies involved. The proposed architecture trains multiple times with several algorithms. To shorten the overall runtimes, the proposed architecture was deployed in Fed4FIRE+ with Ray to distribute the tasks by the available resources. A set of machine learning algorithms and the proposed architecture were assessed. When compared with a baseline scenario, the proposed architecture enabled to increase the accuracy by 11.5% and the precision by 11.2%.

show abstract

Network IDS alert classification with active learning techniques

Vaarandi,

Guerra-Manzanares

2024

Journal of Information Security and Applications

View full text Add to dashboard Cite

Platform Design and Implementation for Flexible Data Processing and Building ML Models of IDS Alerts

Cited by 3 publications

References 28 publications

A New Software Defined Networks (SDN) in IoTs Based Deep Learning Techniques

A New Software Defined Networks (SDN) in IoTs Based Deep Learning Techniques

A Vote-Based Architecture to Generate Classified Datasets and Improve Performance of Intrusion Detection Systems Based on Supervised Learning

Network IDS alert classification with active learning techniques

Contact Info

Product

Resources

About