BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Security and Privacy against ML-Equipped Adversaries
DTSTART:20190131T143000
DTEND:20190131T163000
DTSTAMP:20260510T202346Z
UID:0167fc385a941892f87d93d8f297f2d4cb3e6ac2318d4837d5f7f0ca
CATEGORIES:Conferences - Seminars
DESCRIPTION:Bogdan Kulynych \nEDIC candidacy exam\nExam president: Prof. 
 Rachid Guerraoui\nThesis advisor: Prof. Carmela Troncoso\nCo-examiner: Pro
 f. Martin Jaggi\n\nAbstract\nMachine learning (ML) is now widely used in t
 he technological industry and beyond due to the rise in the efficiency of 
 ML methods\, data collection\, and processing infrastructure. This rise br
 ings benefits to the society\, but also allows to build powerful tools for
  achieving asocial goals\, like invading the privacy of people or manipula
 ting their behavior. In the standard setting studied in adversarial ML an 
 adversary attempts to disrupt the operation\, backdoor\, or learn sensitiv
 e information across the ML training and inference pipeline. Such setting 
 mostly concerns with the security of an ML operator\, and does not fully r
 eflect the challenges of counteracting or preventing asocial uses of ML as
  those mentioned above. This calls for an in-depth study of ML-equipped ad
 versaries.\n\nBackground papers\nWild Patterns: Ten Years After the Rise o
 f Adversarial Machine Learning\nThe Limitations of Deep Learning in Advers
 arial Settings\,\nAttriGuard: A Practical Defense Against Attribute Infere
 nce Attacks via Adversarial Machine Learning\n \n\n\n 
LOCATION:BC 233 https://plan.epfl.ch/?room=BC233
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR