BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Byzantine Resilience and Privacy in Machine Learning
DTSTART:20220510T140000
DTEND:20220510T160000
DTSTAMP:20261002T073743Z
UID:325cfaf3065ddcc0f21713b9bd26c523b0db9e15366bf446ebf60080
CATEGORIES:Conferences - Seminars
DESCRIPTION:Youssef Allouah\nEDIC candidacy exam\nExam president: Prof. Je
 an-Pierre Hubaux\nThesis advisor: Prof. Rachid Guerraoui\nCo-examiner: Pro
 f. Martin Jaggi\n\nAbstract\nIn this proposal\, we analyze the problem of 
 combining two crucial security aspects of distributed machine learning. Th
 e first one is Byzantine resilience\, that is robustness to faulty or adve
 rsarial nodes during training. The second on is differential privacy\, a s
 trong standard for guaranteeing the privacy of databases in machine learni
 ng. For this\, we discuss three existing works. The first two works are se
 parately tackling Byzantine resilience and differential privacy respective
 ly. The third work studies the combination of a specific type of Byzantine
  resilience with differential privacy. Finally\, in light of this analysis
 \, we outline our research proposal.\n\nBackground papers\n\n	Deep Learnin
 g with Differential Privacy (https://arxiv.org/abs/1607.00133)\n	Byzantine
 -Robust Distributed Learning: Towards Optimal Statistical Rates (https://a
 rxiv.org/abs/1803.01498)\n	Differential Privacy and Byzantine Resilience i
 n SGD: Do They Add Up? (https://arxiv.org/abs/2102.08166)\n
LOCATION:BC 010 https://plan.epfl.ch/?room==BC%20010
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR