BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:An Automated Social Graph De-anonymization Technique
DTSTART:20140604T091500
DTSTAMP:20260509T234140Z
UID:d8f89044675fa414bce8247d8f5692d808539948d553355b5f91ad3f
CATEGORIES:Conferences - Seminars
DESCRIPTION:George DANEZIS\, University College London (UCL)\nWe discuss a
  generic and automated approach to re-identifying nodes in anonymized soci
 al networks\, that allows the fast security evaluation of novel anonymizat
 ion techniques. It uses machine learning (decision forests) to matching pa
 irs of nodes in disparate anonymized sub-graphs. The technique uncovers ar
 tefacts and invariants of any black-box anonymization scheme from a small 
 set of examples. Despite a high degree of automation\, classification succ
 eeds with significant true positive rates even when small false positive r
 ates are sought. Our evaluation uses publicly available real world dataset
 s to study the performance of the techniques against real-world anonymizat
 ions strategies\, namely the schemes used to protect datasets of The Data 
 for Development (D4D) Challenge. We show the technique is effective even g
 iven few training examples\, or training examples across different social 
 networks.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR