Unsw-Nb15 Dataset and Machine Learning Based Intrusion Detection Systems

Sonule, Avinash; Kalla, Mukesh; Jain, Amit; Chouhan, Devendra

doi:10.35940/ijeat.c5809.029320

Cited by 19 publications

(9 citation statements)

References 26 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [38], the authors presented a deep learning approach based on a real dataset (N-BaIoT) to detect DDoS attacks on IoT, using a combination of 3 different deep learning classifiers. The authors mentioned that the combination of BiLSTM-CNN has proven to be great combination, achieving the highest accuracy of 89.7%.…”

Section: Ensemble Deep Learning Classificationmentioning

confidence: 99%

“…It has more than (175) thousand records as a training dataset and (82) thousand records as a testing dataset from the different types of attacks. The completely saved records are two million and 540 thousand [38].…”

Section: N-baiot and Unsw-nb15 Datasetsmentioning

confidence: 99%

“…A residual network (ResNet) stacks residual blocks on the pinnacle of each different to shape a network. It is an innovative neural network model, introduced in [38], in their research "Deep residual learning for image recognition". Residual learning is realized by establishing a direct connection between the input and output.…”

Section: Residual Network (Resnet)mentioning

confidence: 99%

See 2 more Smart Citations

An Efficient Intrusion Detection Approach Using Ensemble Deep Learning models for IoT

2023

IJIES

View full text Add to dashboard Cite

The internet of things (IoT) has gained great importance due to its applicability in various daily life applications and its flexible and scalable framework. The wide and spreading use of IoT in the last few years has attracted intruders, who were able to take advantage of the vulnerabilities of any IoT framework due to the absence of robust security protocols. This discourages current and probable investors. Out-of-date intrusion detection models are mainly developed to support information technology systems using built-in, predefined patterns or highly imbalanced datasets. Over the past decade, deep learning models have outperformed traditional machine learning models in attack detection tasks. The biggest challenge in detecting zero-day attacks is determining the best deep-learning classifier. Numerous research initiatives have combined ensemble learning to improve performance, avoid overfitting, and minimize errors. In this work, to address this research gap, we propose a new enhanced meta-learning ensemble deep learning model based on stacking that combines the baseline deep learning models using two tiers of meta-classifiers. Then, conducting several experiments on two recent huge-size different IoT benchmark datasets to evaluate the performance of the proposed model. Different baseline deep learning classifiers are trained for each dataset, and their performance is compared to the proposed ensemble model. The findings show that the proposed ensemble model significantly enhances the classification accuracy of baseline deep-learning models.

show abstract

Section: Ensemble Deep Learning Classificationmentioning

confidence: 99%

Section: N-baiot and Unsw-nb15 Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Intrusion Detection Approach Using Ensemble Deep Learning models for IoT

2023

IJIES

View full text Add to dashboard Cite

show abstract

“…Sebuah fase yang membutuhkan analisis mendalam untuk menemukan anomali dalam lalu lintas jaringan. Deteksi ini melibatkan data pelatihan seperti pencocokan pola, klasifikasi, statistik, analisis deviasi, asosiasi dan lain-lain (Sonule et al, 2020)(Feroz Khan & Anandharaj, 2020.…”

Section: Deteksiunclassified

Impact of Feature Selection Methods on Machine Learning-based for Detecting DDoS Attacks : Literature Review

Faiz¹,

Somantri²,

Supriyono³

et al. 2022

JITE

View full text Add to dashboard Cite

Cybersecurity attacks are becoming increasingly sophisticated and increasing with the development of technology so that they present threats to both the private and public sectors, especially Denial of Service (DoS) attacks and their variants which are often known as Distributed Denial of Service (DDoS). One way to minimize this attack is by using traditional mitigation solutions such as human-assisted network traffic analysis techniques but experiencing some limitations and performance problems. To overcome these limitations, Machine Learning (ML) has become one of the main techniques to enrich, complement and enhance the traditional security experience. The way ML works are based on the process of data collection, training and output. ML is influenced by several factors, one of which is feature engineering. In this study, we focus on the literature review of several recent studies which show that the feature selection process greatly impacts the level of accuracy of this ML. Datasets such as KDD, UNSW-NB15 and others also affect the level of accuracy of ML. Based on this literature review, this study can observe several feature engineering strategies with relevant impacts that can be chosen to improve ML solutions on DDoS attacks.

show abstract

“…Eğitim veri seti 175,341 kayıttan, test veri seti 82,332 kayıttan oluşmaktadır. Orijinal veri seti ise 2,540,044 kayıttan oluşmaktadır(Sonule et al 2020). Eğirim ve test veri setinin saldırı sınıflarına göre dağılımları Tablo 1'de gösterilmiştir.…”

unclassified

Saldırı Tespitinde Makine Öğrenmesi Yöntemlerinin Performans Analizi

TÜRKYILMAZ¹,

Şentürk²

2022

European Journal of Science and Technology

View full text Add to dashboard Cite

Özİnternete olan ilgi son yıllarda inanılmaz derecede artmış ve artmaya devam etmektedir. Bu artışa birde salgın hastalık koşulları eklenince insan hayatını etkileyen her şeyi internet vasıtasıyla yapmaya odaklanılmıştır. İnternete olan ilgi nasıl arttıysa bu ilgiyi suiistimal etmek isteyen kişilerde ve suç ifa edebilecek olan durumdaki faaliyetlerde de artmış ve istikrarlı şekilde artmaya devam etmiştir. Organizasyonların ağ güvenliğini sağlaması çok daha zor hale gelmiştir. Saldırı ve suçlulara karşı ağ güvenliğini sağlamak için birçok farklı güvenlik sistemleri kullanılmaktadır. Saldırı Tespit Sistemleri (STS) ağ güvenliği için kullanılan güvenlik sistemlerden bir tanesidir. STS aynı zamanda akademik dünyada da oldukça ilgi gören konudur. Son yıllarda araştırmacılar daha verimli ve etkin bir STS ortaya koymak için birçok çalışma yapmıştır. Yapılan çalışmalarda bencmark veri seti olarak kullanılan veri setlerinin günümüz şartlarını taşımadığı ve değerlendirmelerde doğru sonuçları vermediği görülmüştür. Bu soruna çözüm olması için 2015 yılında yayınlanan UNSW-NB15 veri seti oluşturulmuştur. Bu çalışmanın amacı STS'yi daha verimli ve etkin hale getirmek için kullanılan makine öğrenmesi yöntemlerinin UNSW-NB15 veri seti kullanılarak incelenmesi ve karşılaştırılmasıdır. Bunu yaparken kullanılan Özellik Seçim yönteminin algoritma performanslarına olan etkisi de değerlendirilmiştir. Çalışma kapsamında, Orange aracını kullanarak makine öğrenmesi yöntemlerinin performansları karşılaştırıldı. Ayrıca elde edilen sonuçlar ile daha önce yapılmış çalışmalar karşılaştıırlmıştır.

show abstract

Unsw-Nb15 Dataset and Machine Learning Based Intrusion Detection Systems

Cited by 19 publications

References 26 publications

An Efficient Intrusion Detection Approach Using Ensemble Deep Learning models for IoT

An Efficient Intrusion Detection Approach Using Ensemble Deep Learning models for IoT

Impact of Feature Selection Methods on Machine Learning-based for Detecting DDoS Attacks : Literature Review

Saldırı Tespitinde Makine Öğrenmesi Yöntemlerinin Performans Analizi

Contact Info

Product

Resources

About