Filters








25,646 Hits in 6.2 sec

Robust network traffic identification with unknown applications

Jun Zhang, Chao Chen, Yang Xiang, Wanlei Zhou
2013 Proceedings of the 8th ACM SIGSAC symposium on Information, computer and communications security - ASIA CCS '13  
In this paper, we cast unknown applications as a specific classification problem with insufficient negative training data and address it by proposing a binary classifier based framework.  ...  Traffic classification is a fundamental component in advanced network management and security.  ...  This paper is aimed to achieve robust network traffic classification with unknown applications, which relaxes the unrealistic assumption that all classes are known to the classifier.  ... 
doi:10.1145/2484313.2484366 dblp:conf/ccs/ZhangCXZ13 fatcat:er2chtmmfrgihf6kev7h2gtnhi

MACHINE LEARNING BASED NETWORK TRAFFIC CLASSIFICATION INCLUDING ZERO DAY TRAFFIC AS A CLASS

UdayakumarBasavaraj Yalawar, Kameswari K
2016 International Journal of Advanced Research  
Material and Methods:- This section presents a robust traffic classification scheme to deal with zero-day applications. .  ...  figure 1 shows the robust traffic classification with unknown discovery and BoF-based traffic classification, the proposed scheme has identified zero-day traffic when performing traffic classification  ... 
doi:10.21474/ijar01/542 fatcat:ti5a5cky2fa3pkmud2k2sd5ltm

Robust Network Traffic Classification

Jun Zhang, Xiao Chen, Yang Xiang, Wanlei Zhou, Jie Wu
2015 IEEE/ACM Transactions on Networking  
A significant challenge to the robustness of classification performance comes from zero-day applications previously unknown in traffic classification systems.  ...  As a fundamental tool for network management and security, traffic classification has attracted increasing attention in recent years.  ...  This section presents a robust traffic classification scheme to deal with zero-day applications. Fig. 1 shows a new framework of RTC.  ... 
doi:10.1109/tnet.2014.2320577 fatcat:vnr3hnrj5fcqziz43g3wszfdlm

Procedures, Criteria, and Machine Learning Techniques for Network Traffic Classification: A Survey

Muhammad Sameer Sheikh, Yinqiao Peng
2022 IEEE Access  
It not only effectively improve the network service identifications and security issues of the traffic network, but also provide robust accuracy and efficiency in different Internet application behaviors  ...  Finally, key findings and open research challenges for network traffic classification are identified along with recommendations for future research directions.  ...  Traffic classification plays a crucial role for network application and intrusion detection identification.  ... 
doi:10.1109/access.2022.3181135 fatcat:of55hyjgbjgl3pjlcp5kk6rcwe

Automated Big Traffic Analytics for Cyber Security [article]

Yuantian Miao, Zichan Ruan, Lei Pan, Yu Wang, Jun Zhang, Yang Xiang
2018 arXiv   pre-print
The new techniques using statistical features, unknown discovery and correlation analytics show promising potentials to deal with big traffic data.  ...  Network traffic analytics technology is a cornerstone for cyber security systems.  ...  applications manually, and 5) compare with the identification results.  ... 
arXiv:1804.09023v1 fatcat:vh3agewlkrc2ji4kcrg4si26sm

Network traffic classification for data fusion: A survey

Jingjing Zhao, Xuyang Jing, Zheng Yan, Witold Pedrycz
2021 Information Fusion  
Shortly, high efficiency, low cost, unknown application identification, fine granularity with ensured accuracy, encrypted traffic classification, classification with small labeled data and advanced robustness  ...  Third, the identification of unknown network applications becomes crucial, especially for security intrusion, attack and threat detection.  ... 
doi:10.1016/j.inffus.2021.02.009 fatcat:sjlqnax7treyjc2karkqsgxjcq

Analysis of service-oriented traffic classification with imperfect traffic classification methods

Vivek.A Vivek.A
2013 IOSR Journal of Computer Engineering  
Typically the traffic through the network is heterogeneous and it flows from multiple utilities and applications Considering todays threats in network there is yet not a single solution to solve all the  ...  Main advantages of this method are robustness, accuracy, a limited use of processing power, reduced memory requirements in classifying the false positive and false negative from the network traffic and  ...  ., a protocol state machine), it has proved being extremely effective and robust with respect to traffic classification [4] , thanks to an extension that enables management of lookup tables, originally  ... 
doi:10.9790/0661-01030110 fatcat:mxs7bdsy2jfd7hyb3qdvmk7era

Self-Learning Network Intrusion Detection

Konrad Rieck
2011 it - Information Technology  
Empirically, this ability can be demonstrated on real network traffic, where a prototype of the framework identifies 80-97% of unknown attacks with less than 0.002% false positives and throughput rates  ...  In this article, we present a framework for self-learning intrusion detection, which allows for automatically identifying unknown attacks in the application layer of network communication.  ...  The ability to detect unknown network attacks can be empirically demonstrated on real network traffic and attacks.  ... 
doi:10.1524/itit.2011.0637 fatcat:oqg3zppeljh2xnqgs7jw7qin4q

Realtime Encrypted Traffic Identification using Machine Learning

Chengjie Gu, Shunyi Zhang, Yanfei Sun
2011 Journal of Software  
By experiment results and analysis, this method can classify online encrypted network traffic with high accuracy and robustness.  ...  The emergence of many new encrypted applications which use dynamic port numbers and masquerading techniques causes the most challenging problem in network traffic identification field.  ...  At the same time, the average identification accuracy of unknown P2P traffic is 86.28%, which indicates that the methods can classify encrypted P2P traffic with considerable accuracy.  ... 
doi:10.4304/jsw.6.6.1009-1016 fatcat:4gm7pdcplvdltl5h2ujbfm3oxy

The Analysis and Identification of P2P Botnet's Traffic Flows

Wernhuar Tarng, Li-Zhong Deng, Kuo-Liang Ou, Mingteh Chen
2011 International Journal of Communication Networks and Information Security  
The objective of this study is to identify the traffic flows produced by known or unknown malicious software for defending against P2P botnets.  ...  Thus, it is an important subject regarding network security to detect and defend against the botnets.  ...  robustness.  ... 
dblp:journals/ijcnis/TarngDOC11 fatcat:wqamwellovgb3pvihb373exphu

Identification and Analysis of Peer-to-Peer Traffic

Marcell Perényi, Trang Dinh Dang, András Gefferth, Sándor Molnár
2006 Journal of Communications  
Recent measurement studies report that a significant portion of Internet traffic is unknown.  ...  First, we propose a novel identification method to reveal P2P traffic from traffic aggregation.  ...  ACKNOWLEDGMENT The authors are grateful to Ericsson Hungary Ltd. for the financial support, to Magyar Telekom for their help in the traffic measurement and to István Maricza for his useful comments on  ... 
doi:10.4304/jcm.1.7.36-46 fatcat:hf4mhf3x3ffsrdiw323q3cb2m4

Multi-levels traffic classification technique

Chengjie Gu, Shunyi Zhuang, Yanfei Sun, Junrong Yan
2010 2010 2nd International Conference on Future Computer and Communication  
However, as many newly-emerged P2P applications use dynamic port numbers and masquerading techniques, it causes the most challenging problem in network traffic classification.  ...  by variety of network activities and their requirements of traffic.  ...  The dynamic classification and identification of network applications responsible for network traffic flows is essential to IP network engineering.  ... 
doi:10.1109/icfcc.2010.5497751 fatcat:g55n64uhsrdyrccuf3mfd7yaq4

On the Identification and Analysis of P2P Traffic Aggregation [chapter]

Trang Dinh Dang, Marcell Perényi, András Gefferth, Sándor Molnár
2006 Lecture Notes in Computer Science  
First, we propose a novel identification method to reveal P2P traffic from traffic aggregation. Our method is based on a set of heuristics derived from the robust properties of P2P traffic.  ...  Our results show that the unique properties of P2P application traffic seem to fade away during aggregation and characteristics of the traffic will be similar to that of other non-P2P traffic aggregation  ...  The flag has the default value of u which means unknown (traffic) and it can be changed in the course of the identification process.  ... 
doi:10.1007/11753810_51 fatcat:di3z5raz6nftjjecerbzwbx5vm

Service-based traffic classification: Principles and validation

M. Baldi, A. Baldini, N. Cascarano, F. Risso
2009 2009 IEEE Sarnoff Symposium  
This paper presents a novel approach in traffic classification that is based on the identification of the service that generates the traffic.  ...  Experimental results on real traffic confirm that this method is extremely effective and may improve considerably the accuracy of traffic classification, while it is suitable to a large number of applications  ...  Observed sessions 40503 Observed services 21675 Observed applications 81 Services with univocally classified sessions 21042 Services with least one unknown session 633 While the session  ... 
doi:10.1109/sarnof.2009.4850330 fatcat:puu55xdwwnb5zjcsuwffjh5hiu

Online Self-learning Internet Traffic Classification based on Profile and Ontology

Chengjie GU, Shunyi ZHANG, Xiaozhen XUE
2011 Journal of Convergence Information Technology  
Prior traffic analysis is an essential requirement for existing classification schemes to classify unknown traffic.  ...  Experiment results illustrate this method can reason from existing knowledge on traffic classification for achieving an automatic traffic classification with high accuracy.  ...  Classifying unknown P2P traffic The purpose of this section is to verify whether the proposed method is robust or flexible enough to detect unknown P2P traffic.  ... 
doi:10.4156/jcit.vol6.issue4.10 fatcat:gdj332gqmngoxcfuqkbjovwdfi
« Previous Showing results 1 — 15 out of 25,646 results