Characterization of Encrypted and VPN Traffic using Time-related Features

Draper-Gil, Gerard; Lashkari, Arash Habibi; Mamun, Mohammad Saiful Islam; Ghorbani, Ali A.

doi:10.5220/0005740704070414

Cited by 681 publications

(388 citation statements)

References 0 publications

Supporting

Mentioning

327

Contrasting

Unclassified

Order By: Relevance

“…Scenario A: The dataset was created by A. Lashkari et al by merging Tor traffic dataset [7] and a public dataset of encrypted traffic generated by Draper-Gil et al [31] which included the same application on the same network. The Tor traffic dataset flows were labelled Tor and all flows from Draper et al [31] as nonTor.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approach for Detectionof nonTor Traffic

Hodo¹,

Bellekens

Iorkyase³

et al. 2017

JCSM

View full text Add to dashboard Cite

Intrusion detection has attracted a considerable interest from researchers and industry. After many years of research the community still faces the problem of building reliable and efficient intrusion detection systems (IDS) capable of handling large quantities of data with changing patterns in real time situations. The Tor network is popular in providing privacy and security to end user by anonymizing the identity of internet users connecting through a series of tunnels and nodes. This work identifies two problems; classification of Tor traffic and nonTor traffic to expose the activities within Tor traffic that minimizes the protection of users in using the UNB-CIC Tor Network Traffic dataset and classification of the Tor traffic flow in the network. This paper proposes a hybrid classifier; Artificial Neural Network in conjunction with Correlation feature selection algorithm for dimensionality reduction and improved classification performance. The reliability and efficiency of the propose hybrid classifier is compared with Support Vector Machine and naïve Bayes classifiers in detecting nonTor traffic in UNB-CIC Tor Network Traffic dataset. Experimental results show the hybrid classifier, ANN-CFS proved a better classifier in detecting nonTor traffic and classifying the Tor traffic flow in UNB-CIC Tor Network Traffic dataset.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The Tor traffic dataset flows were labelled Tor and all flows from Draper et al [31] as nonTor. The experiment was performed by training ANN, ANN-CFS, SVM, SVM-CFS, NB and NB-CFS with UNB-CIC Tor and nonTor Network Traffic dataset to detect nonTor Traffic in a Tor network.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Approach for Detectionof nonTor Traffic

Hodo¹,

Bellekens

Iorkyase³

et al. 2017

JCSM

View full text Add to dashboard Cite

show abstract

“…This system style has been created absolutely supported the construct of project, this framework will tell you overall work of the net website or project , it describes the full income and outcome of project and the whole methodology of the projects beside, buying product, adding products to cart, payments , delivery of products and put together the chat happen between the client and businessperson [1]. Register login, display roduct, uploading product, Payment gateway payment success error user vendor UN success add to cart amount owing to businessperson requesting for chat [2].…”

Section: System Architecturementioning

confidence: 99%

Providing a Live Chat on Online Shopping with End-to-End Encryption

Manigandan¹,

Latha²,

S.MohamedAsik³

et al. 2018

IJET

View full text Add to dashboard Cite

In our these days life on-line purchase associated e-commerce website has changing into an mandatory things in our daily life vogue since, it conjointly have some major issue like purchasing a product with unhappy mode and lack of data in product usage. therefore as to overcome these drawback we have a tendency to have new entranceway referred to as live chat in on-line looking. We have a tendency to will offer this live chat in most safest method exploitation the end to finish cryptography methodology , most of the looking can have a live chat however they Weren’t provided a cut price options and most e-commerce website don’t have Chat choices. We have a tendency to will even enable the client and producer to Share their thoughts.

show abstract

“…The time-related feature VPN/non-VPN data set used in this work is based on the data sets from the ISCX Research Center of University of New Brunswick, Canada [12]. In this paper, the multi-label classification models were trained to classify network traffic flows into seven application categories including browsing, chat, file transfer, email, peer-topeer, media streaming and voice over IP.…”

Section: Data Setsmentioning

confidence: 99%

Comparison of machine-learning algorithms for classification of VPN network traffic flow using time-related features

Fang

Kalaimannan

Bagui

et al. 2017

Journal of Cyber Security Technology

View full text Add to dashboard Cite

Network traffic classification and characterisation is playing an increasingly vital role in understanding and solving securityrelated issues in internet-based applications. The priority of research studies in this area has focused on characterisation of network traffic based on various layers of communication protocols as outlined in the TCP/IP stack and even further expanded to concentrate on specific application-layer protocols. Virtual Private Networks (VPNs) have become one of the most popular remote access communication methods among users over the public internet and other Internet Protocol (IP)-based networks. VPNs are governed by IP Security, which is a suite of protocols used for tunnelling the already encrypted IP traffic, to guarantee secure remote access to servers. In this paper, we propose and develop a framework to classify VPN or non-VPN network traffic using timerelated features. Our focus is on classification of network traffic which is encrypted, tunnelled through a VPN, and the one which is normally encrypted (non-VPN transmission), using machine-learning techniques on data sets of time-related features. Six classification models: logistic regression, support vector machine, Naïve Bayes, k-nearest neighbour and ensemble methodsthe Random Forest (RF) classifier and Gradient Boosting Tree (GBT) classifiersare compared, and recommendations of optimised RF and GBT models over other models are provided in terms of high accuracy and low overfitting. Features which contributed to achieve 90% accuracy in each category were also identified.

show abstract

Characterization of Encrypted and VPN Traffic using Time-related Features

Cited by 681 publications

References 0 publications

Machine Learning Approach for Detectionof nonTor Traffic

Machine Learning Approach for Detectionof nonTor Traffic

Providing a Live Chat on Online Shopping with End-to-End Encryption

Comparison of machine-learning algorithms for classification of VPN network traffic flow using time-related features

Contact Info

Product

Resources

About