Hierarchical learning for fine grained internet traffic classification

Grimaudo, Luigi; Mellia, Marco; Baralis, Elena

doi:10.1109/iwcmc.2012.6314248

Cited by 39 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset introduced in Section 2 was used for all the experiments presented in this section. We used WEKA (University of Waikato, n.d.) with ten-fold crossvalidation for reliability, as in previous studies (Grimaudo, Mellia, & Baralis, 2012;Hullár, Laki, & György, 2011). More in detail, in a ten-fold cross-validation, the data used for the experiment is partitioned to ten equal-sized pieces in a random fashion.…”

Section: Discussionmentioning

confidence: 99%

A Hybrid Classifier with a Binning Method for Network Application Identification

Moon

Albalawi

Kim

et al. 2014

Journal of Integrated Design and Process Science

View full text Add to dashboard Cite

Despite the increasing interest in application identification, the traditional approach based on transport layer port numbers has become less effective due to several reasons including the increasing use of random or non-standard port numbers and tunneling (e.g., HTTP tunnels). One approach to overcome this is to inspect application payload information. While highly accurate, it is limited and complicated for encrypted or obfuscated packets. Another common approach is to utilize flow statistics, such as flow size and duration, for classifying applications. Since it does not require to read packet contents, this approach has no limitation to plain-text flows, but it is known to be relatively less accurate.In this work, we develop a framework that incorporates those multiple classification techniques to offer accurate identification of applications with greater flexibility. In particular, we present our design of the hybrid classifier that performs classification based on machine learning with payload information and statistical flow-level features. With a recently collected traffic data set with a diverse set of applications, our experimental results show that our hybrid approach provides a high degree of accuracy for application identification yielding an accuracy of 95% on average. In addition, we propose an optimization technique with a novel binning method that partitions the given application set into multiple subgroups to improve the overall identification accuracy. Suh has over 20 years of higher education teaching and research experience in computer programming, data mining, database systems, computer operating systems, automata and formal language theory, network programming, artificial intelligence, data warehousing, systems design and analysis, and expert systems. He currently serves as President of the Society for Design and Process Science which is a professional organization with focus on transdisciplinary research.Wang-Hwan Lee received B.E. degree in Electronic Engineering from Kyungpook National University. From 1983 to 1999, he was a researcher working for ETRI, Korea, and participated in various projects in the areas of telecommunications and network technologies. He is currently an executive director in the Department of Project Planning and Adjustment at SYSMATE Inc. His main working area is concentrating on hadoop and mapreduce network traffic analytics. He currently serves the role of chief project leader of the IT R&D program of MOTIE/KEIT [10041548, "240Gbps real-time automatic signature generation system for application traffic classification supporting over 95% completeness and accuracy".

show abstract

Section: Discussionmentioning

confidence: 99%

A Hybrid Classifier with a Binning Method for Network Application Identification

Moon

Albalawi

Kim

et al. 2014

Journal of Integrated Design and Process Science

View full text Add to dashboard Cite

show abstract

“…Results (pertaining to each single classifier in the hierarchy separately) show that the proposed approach achieves precision and recall ≥ 95% in P2P/non-P2P recognition and ≥ 93% in P2P-type classification, while a recall drop down to 71% is observed at last level. Similarly, Grimaudo et al [8] propose the adoption of a hierarchical classifier to allow Internet TC (into ≥ 20 fine-grained classes), showing a comparison with flat-learning results. The proposed tree-structured (three-level) taxonomy introduces also a first level which identifies known/unseen traffic.…”

Section: Hierarchical Traffic Classificationmentioning

confidence: 99%

“…In this paper, we adopt the top-down choice (similarly to [8]). In this case, for each instance to be classified, the HC framework first predicts its first-level (most generic) class, then it uses that predicted class to narrow the choices of classes to be predicted at the second level (i.e.…”

Section: Preliminaries and Proposed Hc Frameworkmentioning

confidence: 99%

A Dive into the Dark Web: Hierarchical Traffic Classification of Anonymity Tools

Montieri

Ciuonzo

Bovenzi

et al. 2020

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

Privacy-preserving protocols and tools are increasingly adopted by Internet users nowadays. These mechanisms are challenged by the process of Traffic Classification (TC) which, other than being an important workhorse for several network management tasks, becomes a key factor in the assessment of their privacy level, both from offensive (malign) and defensive (benign) standpoints. In this paper we propose TC of anonymity tools (and deeper, of their running services and applications) via a truly hierarchical approach. Capitalizing a public dataset released in 2017 containing anonymity traffic, we provide an in-depth analysis of TC and we compare the proposed hierarchical approach with a flat counterpart. The proposed framework is investigated in both the usual TC setup and its "early" variant (i.e. only the first segments of traffic aggregate are used to take a decision). Results highlight a general improvement over the flat approach in terms of all the classification metrics. Further performance gains are also accomplished by tuning the thresholds ensuring progressive censoring. Finally, fine-grain performance investigation allows to (a) demonstrate lower severity of errors incurred by the hierarchical approach (as opposed to the flat case) and (b) highlight poorly-classifiable services/applications of each anonymity tool, gathering useful feedback on their privacy-level.

show abstract

“…The software is employed for a broader analysis of Internet traffic; therefore, as compared to other classifiers, it is expected to support fewer application protocols. In several studies recently, Tstat has turned out to emerge recreantly in literature as source of ground truth (Finamore et al, 2011;Adami et al, 2012;Grimaudo et al, 2012).…”

Section: Tstatmentioning

confidence: 99%

Online Traffic Measurement and Analysis in Big Data: Comparative Research Review

Ibrahim¹,

Hassan

Ahmad

et al. 2016

American Journal of Applied Sciences

View full text Add to dashboard Cite

Abstract:The Internet traffic measurement and analysis is important to avoid many problems of data transferring via online networks such as data losing and slow data transferring. The Internet traffic measuring and analysis could be effective to avoid the data transferring challenges. The Internet traffic measuring and analysis flexibility is important due to many reasons such as dynamicity of transferred data such as size and format, the data transferring protocols and the dynamicity of measure the traffic based on the networks available resources depend on the transferred data characteristics. The main objective of this paper is to review the most flexible Internet traffic measuring and analysis tools that could be adopted to handle the dynamicity of data transferring characteristics.

show abstract

Hierarchical learning for fine grained internet traffic classification

Cited by 39 publications

References 11 publications

A Hybrid Classifier with a Binning Method for Network Application Identification

A Hybrid Classifier with a Binning Method for Network Application Identification

A Dive into the Dark Web: Hierarchical Traffic Classification of Anonymity Tools

Online Traffic Measurement and Analysis in Big Data: Comparative Research Review

Contact Info

Product

Resources

About