BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Strong Asymptotic Composition Theorems for Mutual Information Meas
 ures
DTSTART:20230301T163000
DTEND:20230301T173000
DTSTAMP:20260408T050636Z
UID:89d9557d566918ebd42da906d3a5ea90ea04994226c3181e5424fa36
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Ibrahim Issa American University of Beirut\nAbstract: Co
 nsider a system containing sensitive information X\, an adversary interact
 ing with the system to obtain Y\, and an information leakage measure deno
 ted by L(X→Y). One of the key challenges in privacy and security problem
 s is to characterize the growth of L(X→Yn) when the adversary makes mult
 iple observations\; such results are called composition theorems. We chara
 cterize this growth when the observations are conditionally independent an
 d identically distributed given X\, and the leakage measure is any of the 
 Sibson and Arimoto mutual informations or α-maximal leakage\, of any orde
 r that is at least unity. Each of these measures increases exponentially 
 fast to a limit that is order and measure-dependent\, with an exponent tha
 t is order- and measure-independent (related to the Chernoff information).
  For the special case of binary X and the maximal leakage metric\, we deri
 ve an adaptive composition theorem\, i.e.\, the adversary interacts with t
 he system in stages: At each stage i\, the adversary may choose an action
  to interact with the system containing X to obtain Yi. The action may dep
 end on previous realizations of the observations\, but the leakage at each
  stage is limited. We bound the maximal leakage from X to Yn in terms of
  the leakage of each stage. Notably\, the upper bound is achieved when the
  observations are conditionally independent outputs of the binary erasure 
 channel (with an appropriate parameter).\n=====\nIbrahim Issa is currently
  a visiting professor with the Laboratory for Information in Networked Sy
 stems (LINX) at EPFL (for Spring 2023)\, and an assistant professor at the
  Electrical and Computer Engineering department at the American Universit
 y of Beirut (since January 2019). Prior to this\, he finished his PhD in A
 ugust 2017 at the School of Electrical Engineering at Cornell University (
 Ithaca\, NY)\, where his thesis on information leakage earned the Outstand
 ing ECE PhD Thesis Research Award. He then joined LINX at EPFL as a postdo
 ctoral researcher from August 2017 to December 2018. His research interest
 s include privacy and security\, information theory\, machine learning\, a
 nd quantum information theory.  \n\n\n 
LOCATION:INM 202 https://plan.epfl.ch/?room==INM%20202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR