BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Lecture
DESCRIPTION:Cryptographically Verified AI/ML Audits -\nIs this company's AI
 /ML model biased? Are its predictions reliable? Are they using my data resp
 onsibly? As AI/ML is deployed in sensitive applications\, it is increasingl
 y important to audit models to ensure that they uphold societal values. How
 ever\, AI/ML service providers almost never release their models or data to
  other parties for auditing due to intellectual property and data privacy i
 ssues. My work aims to address this tension through privacy-preserving cryp
 tographic 'contracts' which can bind service providers' models. These contr
 acts use zero-knowledge proofs and other cryptographic tools to guarantee t
 hat (i) the model satisfies an important property such as group fairness\, 
 robustness\, or differential privacy\; (ii) outside parties can view the co
 ntract to verify whether the model has the property\, but they learn no inf
 ormation about the model parameters or data by doing so. Cryptographic veri
 fication is powerful but computationally expensive\, especially for larger 
 models. In this talk I will introduce a variety of optimization strategies 
 that I've employed in my research to enable this critical emerging approach
  to AI/ML regulation.\n\nBio: Olive Franzese-McLaughlin is a distinguished 
 postdoctoral fellow at the Vector Institute & University of Toronto\, where
  she studies cryptographically verifiable AI/ML regulation. She completed h
 er PhD in applied cryptography at Northwestern and worked as a visiting pro
 fessor at Reed College while ABD\, following an MSci and BA in computationa
 l biology at University of Maryland and Reed College respectively. In addit
 ion to the Vector Distinguished Postdoctoral Fellowship\, Olive was awarded
  an NSF GRFP\, an NCI Cancer Research Training Award\, and a Top 10 Researc
 h Highlight of 2022-23 recognition from the Alan Turing Institute. She has 
 publications in top conferences in machine learning\, computer security\, a
 nd computational biology. Olive has advised projects with several liberal a
 rts college students\, and is looking for motivated research assistants to 
 help investigate cryptographically verified AI/ML.
DTEND:20251112T004000Z
DTSTAMP:20260415T042258Z
DTSTART:20251111T234000Z
GEO:45.480972;-122.630792
LOCATION:Eliot Hall\, 314
SEQUENCE:0
SUMMARY:Computer Science Colloquium: Olive Franzese-McLaughlin '17\, Vector
  Institute
UID:tag:localist.com\,2008:EventInstance_51081938798017
URL:https://events.reed.edu/event/copy-of-computer-science-colloquium-nirva
 n-tyagi-university-of-washington
END:VEVENT
END:VCALENDAR