BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Quantum-Resilient Distributed Learning on Neural-Networks
DTSTART:20190730T090000
DTEND:20190730T110000
DTSTAMP:20260406T171949Z
UID:c45cd1ea1975dcd6d1f65a6fcb079992066106e3c470581effb69ad8
CATEGORIES:Conferences - Seminars
DESCRIPTION:Sinem Sav\nEDIC candidacy exam\nExam president: Prof. Carmela 
 Troncoso\nThesis advisor: Prof. Jean-Pierre Hubaux\nCo-examiner: Prof. Mar
 tin Jaggi\n\nAbstract\nThe growing popularity of distributed machine learn
 ing services has increased the concerns about privacy and security as the 
 data to be collected\, shared\, and trained is generally very sensitive. O
 rganizations/individuals try to increase the size of the training set by c
 ollaboratively train their datasets. In this work\, we propose a method fo
 r protecting the collaborative parties` data in training process. This met
 hod employs lattice-based cryptography and homomorphic operations on encry
 pted data.\n\nBackground papers\nSecureML: A System for Scalable Privacy-P
 reserving Machine Learning\, by  P. Mohassel and Y. Zhang.\nHelen: Malici
 ously Secure Coopetitive Learning for Linear Models\, by Zheng\, W.\, Popa
 \, R. A.\, Gonzalez\, J. E.\, Stoica\, I.\nDeep Learning with Differential
  Privacy\, by Abadi\, M.\,  et al.\n 
LOCATION:BC 229 https://plan.epfl.ch/?room==BC%20229
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR