BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Breaking Differential Privacy with a Stopwatch: Attacks and Formal
  Defenses
DTSTART:20260312T101500
DTEND:20260312T113000
DTSTAMP:20260416T025331Z
UID:8119878860243ed5dd6aa7a9a0564070b82a67c19da54358da3f0f58
CATEGORIES:Conferences - Seminars
DESCRIPTION: Zachary Ratliff \, Harvard University\nDifferential privacy
  (DP) provides a rigorous foundation for protecting individual privacy in 
 statistical data analysis and is now a cornerstone of privacy-preserving s
 ystems. Intuitively\, DP ensures that an algorithm’s output will not cha
 nge in a meaningful way if any single individual’s data is added or remo
 ved from the input. However\, real-world implementations of DP often leak 
 exploitable information through observable behaviors beyond the algorithm
 ’s output\, which are not considered by standard proofs that establish D
 P guarantees. One particularly important example is timing side channels\,
  which arise when an adversary can observe a DP algorithm’s runtime. \n
 \nThis talk is based on joint work appearing in CCS’24 (Distinguished Ar
 tifact Award\, joint with Salil Vadhan)\, CCS’25 (joint work with Nicola
 s Berrios and James Mickens)\, and TCC’25 (joint work with Salil Vadhan)
 .  Please see abstract for more details
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/3283858515?omn=65124728469
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR