An efficient user identification approach based on Netflow analysis

Bakhshandeh, Atieh; Eskandari, Zahra

doi:10.1109/iscisc.2018.8546856

Cited by 5 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CTU- 13 After observing the results from the Weka and R Studio tools it is concluded that Weka is better compared to R Studio for classification of NetFlows. The J48 and RF algorithms were used on CTU-13 and PantHoney dataset for classification.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

NetFlow based Cyber Threat Classification using J48 and Random Forest Machine Learning Algorithms

Kumar¹,

Singh²

2019

IJEAT

View full text Add to dashboard Cite

In the field of information technology cyber security plays a vital role. Securing information is the biggest challenge now a days. As the word cyber security comes in our mind the fear of cybercrime comes in us at the same time. Cyber threats are nothing but an activity by which any targeted system can be compromised by altering the availability, integrity, and confidentiality of the system. To overcome such type of threats there are number of mechanisms available. Recently the Machine Learning (ML) approaches have proved to be a milestone for the classification of NetFlows. The NetFlow is a network protocol designed by CISCO which is used to collect the network traffic (NetFlows). In this paper J48 and Random Forest (RF) machine learning algorithms are used for classification of cyber threats using NetFlows. The results are obtained by applying classification algorithms on NetFlows using Weka ML tool and RStudio. A comparison is made in various perspectives like accuracy, true positive (TP), false positive (FP), etc

show abstract

Section: Discussionmentioning

confidence: 99%

“…These methods are not practically feasible because they have not the capacity to process a large amount of traffic. The authors have used data captured from their own setup and after applying the RF technique got the accuracy of 94.60% [13]. Jiangpan et al…”

Section: Related Workmentioning

confidence: 99%

NetFlow based Cyber Threat Classification using J48 and Random Forest Machine Learning Algorithms

Kumar¹,

Singh²

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…When the routers are utilized, the NetFlow can generate NetFlow records. NetFlow collector utilized to group the records data, which are exported from the router, then process it to perform the traffic analysis and presentation in simple format [24].NetFlow has the switching feature, which helps to export it UDP or SCTP protocols. NetFlow utilized for:  Provide aggregation features using the NetFlow collector.…”

Section: ) Netflowmentioning

confidence: 99%

Analysis of How Scalable Features in Hadoop / MapReduce by Internet Traffic Management

Jacob¹,

Tharwat²,

Fudzee³

et al. 2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Internet traffic monitoring is to measure and analyze the network bottlenecks to manage the online data are transferring processes efficiently. Various tools have been developed by using internet traffic measurement and internet traffic analysis tools, such as Hadoop. Activity measurement and adaptive examination represent the dynamics of information exchange. On the other hand, information exchange and dynamics measure movement in light of the system assets that can be accessed depending on the characteristics of the exchanged information. The main aim of this work is to apply scalable features of internet traffic measurement and analysis using Hadoop to understand the effects of these features on the speed of transferring data. This gives a new vision or opportunity to dynamically adapting the most suitable traffic measurement and analysis feature according to network capabilities and environment. This research employs Hadoop/Map Reduce as scalable internet traffic measurement and analysis tools. The simulation was conducted by using five personal computers; one as a server and four virtual computers as network nodes. Each computer has 2GB memory and 100GB storage. Five types of data segmentation are utilized 10 MB, 40MB, 64MB, 200MB, and500MB. The speed of the network is calculating in a megabit per second (Mbs) based upon the network speed on the number of allocated PCs (100 Mbs/4). The simulation is conducted to test the data transfer time based on various selections of network capabilities such as transferring extensive data through a network of medium and heavy usage.

show abstract

“…Bakhshandeh et al [19] showed that identifying the users based on their behavior instead of IP addresses is vital since the dynamic assignation of addresses can easily avoid security mechanisms. The authors proposed a method for efficient user identification method that is based on NetFlow traffic flows.…”

Section: Related Workmentioning

confidence: 99%

Smart User Consumption Profiling: Incremental Learning-Based OTT Service Degradation

et al. 2020

View full text Add to dashboard Cite

Data caps and service degradation are techniques used to control subscribers' data consumption. These techniques have emerged mainly due to the growing demands placed on the networking stack created by the continuous increase in the number of connected users and their feature-rich, bandwidth-heavy Over-the-Top (OTT) applications. In the mobile network's scope, where traditional operators offer user data plans with limited resources, service degradation is a standard mechanism used to throttle consumption. Limiting user data usage helps to utilize resources better and to ensure the network's reliable performance. Nevertheless, this degradation is applied in a generalized way, affecting all user applications without considering behavior. In this paper, we propose a reference model aiming to address this constraint. Specifically, we attempt to personalize service degradation policies by providing a guideline for users' OTT consumption behavior classification based on Incremental Learning (IL). We evaluated our model's viability in a case study by investigating the efficacy of several IL algorithms on a dataset containing realworld users' OTT application consumption behavior. The algorithms include Naive Bayes (NB), K-Nearest Neighbor (KNN), Adaptive Random Forest (ARF), Leverage Bagging (LB), Oza Bagging (OB), Learn++, and Multilayer Perceptron (MLP). The obtained results show that ARF and a composition between LB and ARF achieve the best performance yielding a classification precision and recall of over 90%. Based on the obtained results, we propose service degradation policies to support decision making in missioncritical systems. We argue the strong applicability of our model in real-world scenarios, especially in user consumption profiling. Our reference model offers a conceptual basis for the tasks that need to be performed when defining personalized service degradation policies in current and future networks like 5G. To the best of our knowledge, this work is the first effort in this matter.

show abstract

An efficient user identification approach based on Netflow analysis

Cited by 5 publications

References 3 publications

NetFlow based Cyber Threat Classification using J48 and Random Forest Machine Learning Algorithms

NetFlow based Cyber Threat Classification using J48 and Random Forest Machine Learning Algorithms

Analysis of How Scalable Features in Hadoop / MapReduce by Internet Traffic Management

Smart User Consumption Profiling: Incremental Learning-Based OTT Service Degradation

Contact Info

Product

Resources

About