马德里理工大学招收“在线网络流量分类”(网络通信方向)博士生

中度强迫症者

-----------------------------


TITLE


-----------------------------


Online Network Traffic Classification


 


-----------------------------


KEYWORDS


-----------------------------


Big Data Analytics, Scalability, Network Traffic Classification, Data Stream Mining, Machine Learning


 


-----------------------------


RESEARCH DESCRIPTION


-----------------------------


The research will be conducted at the Technical University of Madrid, within the Internet Next Generation Research Group at E.T.S.I. Sistemas Informaticos and funded by the ONTIC European Project (FP7).


 


Accurate identification and categorization of network traffic according to application type is an important element of many network management and engineering tasks related with QoS, capacity planning and detection of network attacks.


 


Terabytes of data may be transferred through the core network of a typical ISP every day. Moreover, it is expected an exponential growth of more than 50 billions of connected devices to Internet. Therefore, this scenario hampers network data capture and analysis.


 


ONTIC (Online Network TraffIc Characterization) project investigates:


 


1)


A novel architecture of scalable mechanisms and techniques to be able to a) characterize online network traffic data streams, identifying traffic patterns evolution, and b) proactively detecting anomalies in real time when hundreds of thousands of packets per second are processed.


 


2)


A completely new set of scalable offline data mining mechanisms and techniques to characterize network traffic, applying a Big Data analytics approach and using distributed computation paradigms in the cloud on extremely large network traffic summary datasets consisting on trillions of records.


 


Under the context of the project, the proposed Ph.D. project aims at investigating and proposing a new set of online and offline algorithms and machine learning techniques to build autonomous network traffic characterization systems while tackling scalability and real time network traffic issues in a Big Data analytics scenario.


 


-----------------------------


REFERENCES


-----------------------------


 


- Pedro Casas, Johan Mazel, Philippe Owezarski, Unsupervised Network Intrusion Detection Systems: Detecting the Unknown without Knowledge, Computer Communications, Volume 35, Issue 7, 1 April 2012.


 


- Casas, P.; Mazel, J.; Owezarski, P., "Knowledge-independent traffic monitoring: Unsupervised detection of network attacks," Network, IEEE , vol.26, no.1, pp.13,21, January-February 2012.


 


- Johan Mazel, Pedro Casas, Yann Labit, Philippe Owezarski: Sub-Space clustering, Inter-Clustering Results Association & anomaly correlation for unsupervised network anomaly detection. CNSM 2011.


 


- Pedro Casas, Johan Mazel, Philippe Owezarski: On the use of Sub-Space Clustering & Evidence Accumulation for traffic analysis & classification. IWCMC 2011.


 


- Apiletti, D., Baralis, E., Cerquitelli, T., & D’Elia, V. Characterizing network traffic by means of the NetMine framework. Computer Networks, 53(6), 2009.


 


- Nigel Williams, Sebastian Zander, and Grenville Armitage. 2006. A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification. SIGCOMM Comput. Commun. Rev. 36, 5 (October 2006).


 


- Jeffrey Erman, Anirban Mahanti, Martin Arlitt, Ira Cohen, and Carey Williamson. Semi-supervised network traffic classification. In Proceedings of the 2007 ACM SIGMETRICS, 2007.


 


- Nguyen, Thuy TT, and Grenville Armitage. "A survey of techniques for internet traffic classification using machine learning." Communications Surveys & Tutorials, IEEE 10.4 ( 2008 ).


 


 (*) P. Owerzarski, E. Baralis and D. Apilietti are part of the ONTIC Consortium.


 


-----------------------------


SKILLS


-----------------------------


Machine learning, Distributed computing systems, Distributed algorithms, Java and/or C programming


 


-----------------------------


LOCATION AND SALARY


-----------------------------


A Ph.D. studentship for 3 years is available. The monthly gross salary is approximately 1900 Euros. The successful candidate will join the Internet Next Generation Research Group in the E.T.S.I. Sistemas Informaticos at Technical University of Madrid, Spain.


 


Technical University of Madrid (Universidad Politécnica de Madrid, UPM) is the oldest and largest Spanish technical university, with more than 4.000 faculty members, around 38.000 undergraduate students and 6.000 postgraduates. UPM benefits from the heritage of its schools: the most ancient ones were founded in the 18th.century. Nowadays UPM’s Schools cover most of engineering disciplines, as well as Architecture, Computer Science and Geodesy & Cartography. Moreover, UPM as a top quality academic establishment has a strong commitment to R&D and Innovation, boasting over 225 Research Units and over 10 Research Institutes and Technological Centres, contributing significantly to the international scientific community with a high number of journal papers, conference communications, and PhD theses.  The UPM researchers have large expertise in research projects participation both at national and international level.


 


-----------------------------


APPLICATION


-----------------------------


Applicants are requested to submit the documents below by e-mail to ontic-project@eui.upm.es with subject “[PhD.ONTIC] Candidate”.


 


- Resume


- Master thesis


- Master's grades


- Recommendation letters


- Publications (if any)


 


The deadline to accept candidatures is March 14th, 2014.


 


-----------------------------


CONTACT


-----------------------------


Please contact Dr. Alberto Mozo for further information a.mozo@upm.es