An effective genetic algorithm-based feature selection method for intrusion detection systems

Halim, Zahid; Yousaf, Muhammad N.; Waqas, Muhammad; Sulaiman, Muhammad; Abbas, Ghulam; Hussain, Masroor; Ahmad, Iftekhar

doi:10.1016/j.cose.2021.102448

Cited by 87 publications

(44 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…GAs have been used in the area of feature selection to speed up search and avoid local optima. Many studies reported in the literature have shown that methods that use GAs as a research technique have performed better than other methods of selection 12,16,17,19,43–48 …”

Section: Methodsmentioning

confidence: 99%

“…Many studies reported in the literature have shown that methods that use GAs as a research technique have performed better than other methods of selection. 12,16,17,19,[43][44][45][46][47][48] In addition, model selection and hyper-parameter optimization are essential steps in ensuring the high performance of the model. Moreover, finding the best hyperparameters is a problem that is often faced by data analysts.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Upper confidence bound integrated genetic algorithm‐optimized long short‐term memory network for click‐through rate prediction

Souissi

Ghorbel

2022

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

Data on online advertising is rising rapidly due to the fast development of science and technology. Click-through rate (CTR) prediction has become a critical task regarding the digital advertising industry and a key element in increasing advertising profits and user experience. Therefore, this article describes the problem of CTR prediction as a function of sequence classification tasks. Then, we proposed a novel optimization strategy to solve the high-dimensional problem and find a subset of relevant variables to ensure high performance of our model and maximize the number of clicks. Here, we introduced a feature selection and hyper-parameter optimization approach using genetic algorithms (GA) and the upper confidence bound (UCB) model to optimize micro-targeting technology, along with the long short-term memory (LSTM) network-based CTR prediction model. The efficiency of the proposed UCB-LSTM-GA model and two hybrid models, namely LSTM-GA and LSTM-PSO, is evaluated by comparing them to each other and to other machine-learning-based classification methods, including LSTM using a UCB algorithm (UCB-LSTM), High-order Attentive Factorization Machine (HoAFM), genetic algorithm-artificial neural network (GA-ANN), and a feature interaction graph neural network model (Fi-GNN). Our solution achieved as high as 87%, 89%, and 92% for respectively accuracy, precision, and recall, using the popular python tools with real Avazu datasets.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Upper confidence bound integrated genetic algorithm‐optimized long short‐term memory network for click‐through rate prediction

Souissi

Ghorbel

2022

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

show abstract

“…The authors [10], found that the implementation of machine learning methods depends on the validation and availability of data, as the higher dimensionality has an adverse impact on the performance of the machine learning algorithm. The authors developed a genetic algorithm based on a novel fitness function and featuring selection methodology that preserves the information using intrusion detection for network security.…”

Section: Related Workmentioning

confidence: 99%

Optimization of Intrusion Detection Systems Determined by Ameliorated HNADAM-SGD Algorithm

et al. 2022

View full text Add to dashboard Cite

Information security is of pivotal concern for consistently streaming information over the widespread internetwork. The bottleneck flow of incoming and outgoing data traffic introduces the issues of malicious activities taken place by intruders, hackers and attackers in the form of authenticity obstruction, gridlocking data traffic, vandalizing data and crashing the established network. The issue of emerging suspicious activities is managed by the domain of Intrusion Detection Systems (IDS). The IDS consistently monitors the network for the identification of suspicious activities, and generates alarm and indication in the presence of malicious threats and worms. The performance of IDS is improved by using different machine learning algorithms. In this paper, the Nesterov-Accelerated Adaptive Moment Estimation–Stochastic Gradient Descent (HNADAM-SDG) algorithm is proposed to determine the performance of Intrusion Detection Systems IDS. The algorithm is used to optimize IDS systems by hybridization and tuning of hyperparameters. The performance of algorithm is compared with other classification algorithms such as logistic regression, ridge classifier and ensemble algorithms where the experimental analysis and computations show the improved accuracy with 99.8%, sensitivity with 99.7%, and specificity with 99.5%.

show abstract

“…Z. Halim ve ark. [15] yeni bir GA tabanlı öznitelik seçim yönetimi önermişler ve sonuçları dört farklı sınıflandırma algoritmasında test etmişlerdir. 10 öznitelik ile en başarılı sonucu %99.8 ile XgBoost algoritması vermiştir.…”

Section: Literatürdeki İlgili çAlışmalarunclassified

“…Çizelge-1 saldırı ve normal davranışlar için oluşturulan karmaşıklık matrisini göstermektedir. [15]. Şekil-2 genetik algoritma akış diyagramını göstermektedir.…”

Section: Performans Metrikleriunclassified

Genetic Feature Selection Approach in Detection of Web Application Attacks Using Machine Learning Methods

Ahmetoglu

Daş

2021

Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi

View full text Add to dashboard Cite

Applications on the Internet have some coding-related security concerns. Weaknesses or vulnerabilities allow criminals to gain direct and public access to databases to steal sensitive data. This study proposes an approach based on heuristic feature selection and machine learning for easier and more accurate detection of web application attacks with hybrid intrusion detection systems. Web application attacks and benign flow examples in CIC-IDS2017 and CSE-CIC-IDS2018 datasets were combined after a series of data preprocessing stages, and a new dataset was created. Using Genetic Algorithm and LogisticRegression, mean square error and feature count optimization were performed, and the results were tested with five different machine learning algorithms. When the results obtained were examined, it was observed that the success rate in classification remained at the level of 99%, although the number of features was reduced by 85%

show abstract

An effective genetic algorithm-based feature selection method for intrusion detection systems

Cited by 87 publications

References 33 publications

Upper confidence bound integrated genetic algorithm‐optimized long short‐term memory network for click‐through rate prediction

Upper confidence bound integrated genetic algorithm‐optimized long short‐term memory network for click‐through rate prediction

Optimization of Intrusion Detection Systems Determined by Ameliorated HNADAM-SGD Algorithm

Genetic Feature Selection Approach in Detection of Web Application Attacks Using Machine Learning Methods

Contact Info

Product

Resources

About