BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Anomaly Detection in the Field - Christian Callegari (University o
 f Pisa)
DTSTART:20131009T120000Z
DTEND:20131009T130000Z
UID:TALK45347@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:The talk will focus on the challenges that arise when applying
  Statistical Network Anomaly Detection in the field. \nIn more detail thre
 e aspects will be discussed:\n\n- Dealing with huge quantities of data: th
 e explosive growth of the traffic poses several problems when applying tec
 hniques that need to process the whole traffic. We will discuss pros and c
 ons of some data mining techniques (e.g.\, Sketch and Reversible Sketch) t
 hat permits to analyze a data flow\, almost in real-time\, without storing
  all the data. \n\n-Dealing with traffic seasonality: seasonality of the t
 raffic poses several problems in the application of most of the anomaly de
 tection techniques. Some of the most classical approaches (e.g.\, Wavelet 
 analysis) to pre-filter such seasonal components will be discussed\, highl
 ighting the improvements introduced in the system.\n\n-Dealing with distri
 buted environment: highly distributed\, multi-domains environments pose se
 veral constraints to the application of any traffic monitoring techniques 
 (e.g.\, privacy concerns). We will discuss how to deal with them\, so as t
 o respect the legislation\, still being able to effectively perform anomal
 y detection.\n\nBio: Christian CALLEGARI received the B.E. and the M.E. de
 grees in telecommunications engineering and the PhD degree in information 
 engineering from the University of Pisa\, Pisa\, in 2002\, 2004\, and 2008
 \, respectively.\nSince 2005\, he has been with the Dept. of Information E
 ngineering at the University of Pisa\, where he is currently a a post-doc 
 research fellow. In 2006/07\, he was a visiting student research collabora
 tor at the Dept. of Computer Science at ENST Bretagne\, France. He has giv
 en several PhD courses about anomaly detection\, network security\, and st
 atistical traffic classification (both at national and international level
 ) and he has also given several tutorials about anomaly detection in leadi
 ng international conferences.\n
LOCATION:LT2\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR