BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Characterizing the Space of Adversarial Examples in
  Machine Learning
DTSTART:20180409T101500
DTEND:20180409T113000
DTSTAMP:20260511T204813Z
UID:670500e225d36392c58fec76df2d4ef73fdab169b81bd9dddf149df8
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Nicolas Papernot - Pennsylvania State University\nIC Facul
 ty candidate\n\nAbstract:\nThere is growing recognition that machine learn
 ing (ML) exposes new security and privacy vulnerabilities in software syst
 ems\, yet the technical community's understanding of the nature and extent
  of these vulnerabilities remains limited but expanding. In this talk\, I 
 explore the threat model space of ML algorithms\, and systematically explo
 re the vulnerabilities resulting from the poor generalization of ML models
  when they are presented with inputs manipulated by adversaries. This char
 acterization of the threat space prompts an investigation of defenses that
  exploit the lack of reliable confidence estimates for predictions made. I
 n particular\, we introduce a promising new approach to defensive measures
  tailored to the structure of deep learning. Through this research\, we ex
 pose connections between the resilience of ML to adversaries\, model inter
 pretability\, and training data privacy.\n\nBio:\nNicolas Papernot is a Ph
 D student in Computer Science and Engineering working with Professor Patri
 ck McDaniel at the Pennsylvania State University. His research interests l
 ie at the intersection of computer security\, privacy and machine learning
 . He is supported by a Google PhD Fellowship in Security and received a be
 st paper award at ICLR 2017. He is also the co-author of CleverHans\, an o
 pen-source library widely adopted in the technical community to benchmark 
 machine learning in adversarial settings. In 2016\, he received his M.S. i
 n Computer Science and Engineering from the Pennsylvania State University 
 and his M.S. in Engineering Sciences from the Ecole Centrale de Lyon.\n\nM
 ore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR