Feature selection to detect botnets using machine learning algorithms

Alejandre, Francisco Villegas; Cortés, Nareli Cruz; Anaya, Eleazar Aguirre

doi:10.1109/conielecomp.2017.7891834

Cited by 48 publications

(23 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These techniques were mainly used for feature optimization and optimizing the parameter for the classifiers. For example, particle swarm optimization (PSO) was adopted in [18][19][20]; the genetic algorithm (GA) was utilized in [21,22] to enhance the effectiveness of a malware detection system. Table 1 abstracts some characteristics of the discussed malware identification approaches, concerning the focus areas, techniques, features, datasets, and validation metrics used to evaluate the models' performances.…”

Section: Malware Identificationmentioning

confidence: 99%

“…First, the combination of several AI-based techniques in a defense solution may still an interesting research direction. For example, the incorporation of bio-inspired computation and ML/DL approaches shows promising results in malware detection [18][19][20][21][22] or [36][37][38] for detecting the network intrusion. Hence, the combination of these two techniques is a very potential research direction due to the number of bio-inspired algorithms exploited in cybersecurity still being limited.…”

Section: Open Research Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in the Cyber Domain: Offense and Defense

2020

View full text Add to dashboard Cite

Artificial intelligence techniques have grown rapidly in recent years, and their applications in practice can be seen in many fields, ranging from facial recognition to image analysis. In the cybersecurity domain, AI-based techniques can provide better cyber defense tools and help adversaries improve methods of attack. However, malicious actors are aware of the new prospects too and will probably attempt to use them for nefarious purposes. This survey paper aims at providing an overview of how artificial intelligence can be used in the context of cybersecurity in both offense and defense.

show abstract

Section: Malware Identificationmentioning

confidence: 99%

Section: Open Research Directionsmentioning

confidence: 99%

Artificial Intelligence in the Cyber Domain: Offense and Defense

2020

View full text Add to dashboard Cite

show abstract

“…Essas bases são compostas por dados de fluxos do tipo NetFlow [Claise, 2004] [Goldberg, 1989], utilizado no trabalho de [Alejandre et al, 2017], cuja verificação dos efeitos de classificação se baseou no algoritmo Árvore [Alejandre et al, 2017], [Silva et al, 2017] e [Beigi et al, 2014], ratifica-se a característica MedPktSize que aparece em todos. TotBytes só não aparece em [Beigi et al, 2014] e MedBitsSecond não foi selecionada no trabalho de [Alejandre et al, 2017]. Já o atributo SrcBytes aparece, no presente trabalho, como uma nova característica relevante para detectar tráfego de botnet.…”

Section: Metodologia De Avaliaçãounclassified

Abordagem Probabilística À Escolha De Produtos De Defesa: Uma Aplicação Da Composição Probabilística De Preferências Na Aquisição De Blindados

Gavião¹,

Sant’Anna²,

Lima³

et al. 2019

Pesquisa Operacional E Sua Atuação Multidisciplinar

View full text Add to dashboard Cite

show abstract

“…This study is focused on the bidirectional packet size sequence information in order to discover the features and to capture periodical beacon signals sent to the bots. Alejandre et al extracted the feature set from network flows by applying genetic algorithm. The feature set includes 19 statistical flow features, and detection accuracy is evaluated by C4.5 algorithm.…”

Section: Related Workmentioning

confidence: 99%

Botnet detection based on network flow summary and deep learning

Pektaş

Acarman

2018

Int J Network Mgmt

View full text Add to dashboard Cite

A botnet is a group of compromised Internet-connected devices controlled remotely by cyber criminals to launch coordinated attacks and to perform various malicious activities. Since botnets continuously adapt themselves to the evolving countermeasures introduced by both network and host-based detection mechanism, the traditional approaches do not provide adequate protection to botnet threat. On the one hand, behavioral analysis of network traffic can play a key role to detect botnets. For instance, behavioral analysis can be applied to observe and discover communication patterns that botnets operate during their life cycle. On the other hand, deep learning has been successfully applied to various classification tasks, and it is also a promising solution for botnet discovery. In this paper, we apply deep neural network to detect botnet by modeling network traffic flow. The performance of the proposed method is evaluated with publicly available large-scale communication traces. The experimental results illustrate that deep learning is an efficient and effective method for identifying botnet traffic with a high true positive rate (attack detection rate) and low false positive alarm rate.Int J Network Mgmt. 2018;28:e2039.wileyonlinelibrary.com/journal/nem

show abstract

Feature selection to detect botnets using machine learning algorithms

Cited by 48 publications

References 5 publications

Artificial Intelligence in the Cyber Domain: Offense and Defense

Artificial Intelligence in the Cyber Domain: Offense and Defense

Abordagem Probabilística À Escolha De Produtos De Defesa: Uma Aplicação Da Composição Probabilística De Preferências Na Aquisição De Blindados

Botnet detection based on network flow summary and deep learning

Contact Info

Product

Resources

About