An Efficient Intrusion Detection Method Based on LightGBM and Autoencoder

Tang, Chaofei; Luktarhan, Nurbol; Zhao, Yongxia

doi:10.3390/sym12091458

Cited by 54 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Auto Encoder [122], [124], [136], [137] Advantages: Specialized neural network with a "bottleneck" architecture. Suitable for finding an encoding of the input data.…”

Section: Discussionmentioning

confidence: 99%

Intrusion Detection Systems for IoT: opportunities and challenges offered by Edge Computing and Machine Learning

Spadaccino¹,

Cuomo²

2020

Preprint

View full text Add to dashboard Cite

Key components of current cybersecurity methods are the Intrusion Detection Systems (IDSs) were different techniques and architectures are applied to detect intrusions. IDSs can be based either on cross-checking monitored events with a database of known intrusion experiences, known as signature-based, or on learning the normal behavior of the system and reporting whether some anomalous events occur, named anomaly-based. This work is dedicated to the application to the Internet of Things (IoT) network where edge computing is used to support the IDS implementation. New challenges that arise when deploying an IDS in an edge scenario are identified and remedies are proposed. We focus on anomaly-based IDSs, showing the main techniques that can be leveraged to detect anomalies and we present machine learning techniques and their application in the context of an IDS, describing the expected advantages and disadvantages that a specific technique could cause.

show abstract

“…Auto Encoder [122], [124], [136], [137] Advantages: Specialized neural network with a "bottleneck" architecture. Suitable for finding an encoding of the input data.…”

Section: Discussionmentioning

confidence: 99%

Intrusion Detection Systems for IoT: opportunities and challenges offered by Edge Computing and Machine Learning

Spadaccino¹,

Cuomo²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The UNSW-NB15 dataset was used to validate the proposed intrusion detection model. Tang et al [21] proposed an intrusion detection system based on LightGBM and AE. The proposed LightGBM-AE model consists of three steps: data preprocessing, feature selection and classification.…”

Section: Related Workmentioning

confidence: 99%

STLGBM-DDS: An Efficient Data Balanced DoS Detection System for Wireless Sensor Networks on Big Data Environment

Dener

Orman

2022

IEEE Access

View full text Add to dashboard Cite

Wireless Sensor Networks(WSNs) are vulnerable to a variety of unique security risks and threats in their data collection and transmission processes. One of the most common attacks on WSNs that can target all layers of the protocol stack is the DoS attack. In this study, a unique DoS Intrusion Detection System (DDS) is proposed to detect DoS attacks specific to WSNs. The proposed system is an ensemble intrusion detection system called STLGBM-DDS, which is developed on Apache Spark big data platform in Google Colab environment, combining LightGBM machine learning algorithm, data balancing and feature selection processes. In order to reduce the effects of data imbalance on system performance, data imbalance processing consisting of Synthetic Minority Oversampling Technique (SMOTE) and Tomek-Links sampling methods called STL was used. In addition, Information Gain Ratio was used as a feature selection technique in the data preprocessing stage. The effects of both data balancing and feature selection stages on the detection performance of the system were investigated. The results obtained were evaluated using the Accuracy, F-Measure, Precision, Recall, ROC Curve and Precision-Recall Curve parameters. As a result, the proposed method achieved an overall accuracy of 99.95%. Also, it achieved 99.99%, 99.96%, 99.98%, 99.92%, 99.87% accuracy performance according to Normal, Grayhole, Blackhole, TDMA and Flooding classes, respectively. According to the results obtained, the proposed method has achieved very successful results in DoS attack detection in WSNs compared to current methods.

show abstract

“…Cil et al [3], the preprocessing consists of three steps: preparing data like dropping rows and columns with misleading values, normalization where dataset is scaled as either '0' or '1' based on the type of attack and finally splitting the dataset into training and testing sets. Chaofei Tang et al [27] uses one-hot-encoding technology to convert 3 types of non-numeric categorical features: protocol type (tcp, udp,icmp), flag and service into binary vectors.…”

Section: Preprocessingmentioning

confidence: 99%

A Comprehensive survey on Various Machine Learning Models for Anomaly-Based Intrusion Detection System

Sharma¹,

Singh²

2022

Artificial Intelligence and Communication Technologies

View full text Add to dashboard Cite

As a result of the current global pandemic, there has been a surge in the use of various online platforms and services available via the internet. This results in the increase of exposure to different cyber-attacks on the network infrastructures. Cyber threats in the form of malicious software or also known as “malwares” have posed a serious threat to the smooth running of both government and business sectors. To cope with such issues, researchers have come up with various methods of machine learning based techniques in order to detect malicious activity on the network. But the major issue remains with the presence of vast diversity of features that leads to lengthy training processes and the need to deal with the prediction accuracy. This paper presents a literary review of various works on different machine learning-based intrusion detection system presented in different research papers over the last five years. Also, the results obtained from the various works such as evaluated metrics, datasets, and accuracy are discussed and compared. The scope of our review study is to provide a brief idea of intrusion detection as well as a reference to other research works done in the field of machine learning based intrusion detection system. Finally, the issues and future development are discussed by evaluating typical studies from recent years.

show abstract

An Efficient Intrusion Detection Method Based on LightGBM and Autoencoder

Cited by 54 publications

References 27 publications

Intrusion Detection Systems for IoT: opportunities and challenges offered by Edge Computing and Machine Learning

Intrusion Detection Systems for IoT: opportunities and challenges offered by Edge Computing and Machine Learning

STLGBM-DDS: An Efficient Data Balanced DoS Detection System for Wireless Sensor Networks on Big Data Environment

A Comprehensive survey on Various Machine Learning Models for Anomaly-Based Intrusion Detection System

Contact Info

Product

Resources

About