FastDetict: A Data Mining Engine for predecting and preventing DDoS attacks

Nijim, Mais; Khan, Mohammad S.; Rao, D.T.V.

doi:10.1109/ths.2017.7943451

Cited by 16 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…NSL-KDD is a data set that evolved owing to criticization of the KDD99 issues in 2009 (Ng et al , 2016). Because the data set includes a significant number of replicated records, high-frequency threats are likely to be learned while learning methodologies and can also impact test results (Nijim et al , 2017). The current KDD99 data set displays low classifications of threats like U2R or R2L that are detrimental to a real network but are not widely used.…”

Section: Proposed Methodologymentioning

confidence: 99%

An intrusion detection system for health-care system using machine and deep learning

Pande

Khamparia

Gupta

2021

WJE

View full text Add to dashboard Cite

Purpose One of the important key components of health care–based system is a reliable intrusion detection system. Traditional techniques are not adequate to handle complex data. Also, the diversified intrusion techniques cannot meet current network requirements. Not only the data is getting increased but also the attacks are increasing very rapidly. Deep learning and machine learning techniques are very trending in the area of research in the area of network security. A lot of work has been done in this area by still evolutionary algorithms along with machine learning is very rarely explored. The purpose of this study is to provide novel deep learning framework for the detection of attacks. Design/methodology/approach In this paper, novel deep learning is the framework is proposed for the detection of attacks. Also, a comparison of machine learning and deep learning algorithms is provided. Findings The obtained results are more than 99% for both the data sets. Research limitations/implications The diversified intrusion techniques cannot meet current network requirements. Practical implications The data is getting increased but also the attacks are increasing very rapidly. Social implications Deep learning and machine learning techniques are very trending in the area of research in the area of network security. Originality/value Novel deep learning is the framework is proposed for the detection of attacks.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

An intrusion detection system for health-care system using machine and deep learning

Pande

Khamparia

Gupta

2021

WJE

View full text Add to dashboard Cite

show abstract

“…-Denial of Service (DoS) : Attackers try to disrupt legitimate users' access to a particular service or device [28] .…”

Section: Class Imbalance Problem In Intrusion Datamentioning

confidence: 99%

Cost-sensitive stacked auto-encoders for intrusion detection in the Internet of Things

Telikani

Gandomi

2021

Internet of Things

View full text Add to dashboard Cite

Intrusion Detection System (IDS) is an important tool for protecting the Internet of Things (IoT) networks against cyber-attacks. Traditional IDSs can only distinguish between normal and abnormal behaviors. On the other hand, modern techniques can identify the kind of attack so that the appropriate reactions can be carried out against each type of attack. However, these techniques always suffer from the class-imbalance which affects the performance of IDS. In this paper, we propose a cost-sensitive stacked auto-encoder, CSSAE, to deal with class imbalance problem in IDS. CSSAE generates a cost matrix in which a unique cost is assigned to each class based on the distribution of different classes. This matrix is created in the first stage of CSSAE. In the second phase, a two-layer stacked auto-encoder is applied to learn features with better distinguish between the minority and the majority classes. These costs are used in the feature learning of deep learning, where the parameters of the neural network are modified by applying the corresponding costs in the cost function layer. The proposed method is able to perform on both binary-class data and multiclass data. Two well-known KDD CUP 99 and NSL-KDD datasets are used to evaluate the performance of CSSAE. Compared with other IDSs that have not considered class imbalance problem, CSSAE shows better performance in the detection of low-frequency attacks.

show abstract

“…Entretanto, esse estudo se restringiu a ataques DDoS volumétricos. O trabalho de [Nijim et al 2017] argumenta a favor de um sistema que utiliza a mineração de dados para predizer e prevenir ataques DDoS na camada de aplicação. A propostaé priorizar requisições legítimas em detrimento do tráfego de ataque por meio de um mecanismo automático de priorização da comunicação.…”

Section: Trabalhos Relacionadosunclassified

“…No geral, as abordagens embasam-se em técnicas de mineração de dados, modelos estatísticos, redes neurais e modelos de Markov. Por exemplo, [Kwon et al 2017] expõem um método pró-ativo para predizer o volume de ataques DDoS em uma rede através da análise de regressão e correlação, e [Nijim et al 2017] um sistema para predizer ataques DDoS na camada de aplicação pela mineração de dados e classificação das requisições com base no histórico de uso de recursos. [Wang et al 2017] fazem correlações do comportamento temporal, espacial e espaço-temporal dos ataques.…”

Section: Introductionunclassified

Um Sistema Autoadaptável para Predição de Ataques DDoS Fundado na Teoria da Metaestabilidade

Pelloso¹,

tz²,

Santos³

et al. 2018

Anais Do XXXVI Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2018)

View full text Add to dashboard Cite

Os ataques de Negação de Serviço Distribuídos (Distributed Denial of Service - DDoS) crescem significativamente em volume, sofisticação e impacto. Exemplos são os ataques DDoS contra a empresa francesa OVN e o provedor de nomes DYN, os quais atingiram volumes inéditos de tráfego malicioso. Em geral, esses ataques possuem comportamentos inesperados, desta forma são detectados ou mitigados apenas quando se encontram em estágios avançados. Diferente de outros trabalhos, nós advogamos pelo prognóstico precoce de ataques DDoS a fim de evitar custos e perdas provenientes do ataque. Este trabalho apresenta STARK, um sistema autoadaptativo de predição de ataques DDoS, que identifica indícios do ataque na rede antes deste alcançar estágios avançados. Com base na teoria da metaestabilidade, STARK provê um aprendizado estatístico não supervisionado e identifica a iminência de ataques DDoS. A avaliação do STARK segue uma abordagem orientada a traços, em que três bases de dados são utilizadas. Como resultado, STARK demonstra predizer os ataques DDoS com minutos ou horas de antecedência.

show abstract

FastDetict: A Data Mining Engine for predecting and preventing DDoS attacks

Cited by 16 publications

References 1 publication

An intrusion detection system for health-care system using machine and deep learning

An intrusion detection system for health-care system using machine and deep learning

Cost-sensitive stacked auto-encoders for intrusion detection in the Internet of Things

Um Sistema Autoadaptável para Predição de Ataques DDoS Fundado na Teoria da Metaestabilidade

Contact Info

Product

Resources

About