BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:ISP AI Forum: "AI Security & Privacy: The Hype\, State-of-the-
 Art and Open Challenges"
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260914T031519Z
UID:tag:localist.com\,2008:EventInstance_38820949909202
DTSTART:20220318T163000Z
DTEND:20220318T173000Z
DESCRIPTION:Abstract: The adoption of AI systems in daily life and critical
  applications is becoming ubiquitous. This wide availability has at the sa
 me time raise questions about the trustworthiness\, security\, and privacy
  implications of using these systems. While novel technologies and methodo
 logies have been emerging to protect the privacy and security of AI System
 s\, there are still open challenges that need to be addressed by the commu
 nity. Over the past years\, my research has focused on the creation of def
 enses to protect the machine learning pipeline and the design of privacy-a
 ware methodologies to enable the training of accurate machine learning mod
 els without transmitting the training data to a central place. In this tal
 k\, I will first provide an overview of the challenges and threats inheren
 t to the machine learning pipeline in traditional setups where all the tra
 ining data is available in the same place and some mitigation techniques t
 o deter these attacks. In the second part of the talk\, I will cover a gam
 e-changing and privacy-by-design paradigm known as federated learning (FL)
 \, where data owners do not need to share or transfer their data to collab
 oratively train a model. During this part of the talk\, I will present mul
 tiple cutting-edge approaches\, interesting aspects of making FL available
  in a product and some open research directions.\n\nBio:  Nathalie Baracal
 do leads the AI Security and Privacy Solutions team and is a Research Staf
 f Member at IBM’s Almaden Research Center in San Jose\, CA. Nathalie is 
 passionate about delivering machine learning solutions that are highly acc
 urate\, withstand adversarial attacks and protect data privacy. Nathalie h
 as led her team to the design of the IBM Federated Learning framework\, wh
 ich is now part of the Watson Machine Learning product. In 2020\, Nathalie
  received the IBM Master Inventor distinction for her contributions to IBM
  Intellectual Property and innovation. Nathalie also received the 2021 Cor
 porate Technical Recognition\, one of the highest recognitions provided to
  IBMers for breakthrough technical achievements that have led to notable m
 arket and industry success for IBM. This recognition was awarded for Natha
 lie's contribution to the Trusted AI Initiative. Nathalie has received mul
 tiple best paper awards and published in top-tier conferences and journals
 . Nathalie’s research interests include security and privacy\, distribut
 ed systems and machine learning. Nathalie received her Ph.D. degree from t
 he University of Pittsburgh in 2016. \n\nRSVP for the Zoom meeting informa
 tion: https://pitt.co1.qualtrics.com/jfe/form/SV_6nG2s4RNUbtFiWq
LOCATION:
SUMMARY:ISP AI Forum: "AI Security & Privacy: The Hype\, State-of-the-Art a
 nd Open Challenges"
URL;VALUE=URI:https://calendar.pitt.edu/event/isp_ai_forum_365
CATEGORIES:Forums
END:VEVENT
END:VCALENDAR