CORPORATE TALK SERIES
(Principal Researcher, Microsoft Research)
Bio: Nishanth Chandran is a Principal Researcher at Microsoft Research, India. His research interests are in problems related to cryptography, cloud security, confidential computing and secure computation. Prior to joining MSRI, Nishanth was a Researcher at AT&T Labs, and before that he was a Post-doctoral Researcher at MSR Redmond.
Nishanth is a recipient of the 2010 Chorafas Award for exceptional achievements in research and his research has received coverage in science journals and in the media at venues such as Nature and MIT Technology Review. He has published several papers in top computer science conferences and journals such as ACM CCS, Crypto, Eurocrypt, IEEE S&P, and so on. His work on position-based cryptography was selected as one of the top 3 works and invited to QIP 2011 as a plenary talk. Nishanth has served on the technical program committee of all the top cryptography conferences on several occasions and he also holds 6 US Patents. Nishanth received his Ph.D. and M.S. in Computer Science, both from UCLA, and B.E. in Computer Science and Engineering from Anna University (Hindustan College of Engineering), Chennai.
Nishanth is also a top ranking (A grade) All India Radio South Indian Classical (Carnatic) Violinist and has performed at international venues such as the Hollywood Bowl, Los Angeles (as part of legendary sitarist Late Pandit Ravi Shankar’s ensemble) and the Madras Music Academy, Chennai.
Title of the Talk: Privacy-Preserving Machine Learning
Abstract: Can multiple entities compute joint functions on their private data without revealing it in the clear with any other entity? Cryptography provides an answer to this intriguing question through the primitive of secure multi-party computation (MPC). A fascinating use-case of MPC is the task of privacy preserving machine learning. A patient can obtain a diagnosis of his/her disease from the owner of an ML model for the disease without revealing his/her private medical information to the model owner nor learning anything else about the ML model. Such a technology could be invaluable towards realizing the full potential of Machine Learning as a Service.
In this talk, I will provide an overview of the area of privacy preserving machine learning. I will also describe a system CrypTFlow, developed at Microsoft Research India, that for the first time, enables such privacy preserving machine learning at the scale of the ImageNet dataset.
(VP of Technology at Cober, Inc.)
Bio: Matthew Krieger is a technologist and executive with experience in IT, manufacturing and publishing. He is VP of Technology for Cober, Inc. and previously held senior IT leadership positions at Time, Inc. and the Reader’s Digest Association. Matt is Chief Technology Officer and sits on the Operating Committee of the SCORE Fairfield County Connecticut chapter, provides CTO guidance for TeenSmart International, and is on the Southern Connecticut State University Computer Science Technical Advisory Committee. Matt is also President of the Reader’s Digest Partners for Sight Foundation non-profit, is on the advisory board of Cyber-Seniors and until recently served on the Advisory Board for the Baruch College Computer Center for Visually Impaired People, having been part of a team that successfully transitioned the Center to a new home. Matt is a frequent presenter on topics of business and technology. Matt is also creator of Whysper, a platform allowing the consumption of web content as text-to-speech podcasts.
(CHO at Google, Software Engineer, Physicist)
Bio:Boris Debić is a Google technologist since 2005. He holds an M.Sc. in Physics from the University of Zagreb, Croatia. At Google he has worked in several roles: Release engineering, G+Privacy, Global Infrastructure, Data center site location, Ads serving infrastructure and now as CHO of Google. He has worked with Google.org on analysis and exchange of global climate modeling data sets and agricultural data to provide food security forecasts. Currently works on projects for Developer Relations. With support from NASA Ames directs Mars Society’s NorCal Rover project. He is a board member of several high tech startup companies in both the US and Croatia including ProductionPro which was featured in the top three best startups at Launch Fest in San Francisco. Prior to Google he has held positions in: Silicon Valley startups, most notably E.piphany; the United Nations; the Croatian Ministry of Foreign Affairs and the University of Zagreb. Boris Debić has been a lecturer, keynote speaker and frequently organizes conferences about Computer Science. He was also a frequent host on Talks at Google.
|Full Paper Submission:||28th September 2020|
|Acceptance Notification:||9th October 2020|
|Final Paper Submission:||17th October 2020|
|Early Bird Registration:||16th October 2020|
|Presentation Submission:||25th October 2020|
|Conference:||4 - 7 November 2020|
• Conference Proceedings will be submitted for publication at IEEE Xplore® digital library .
• Best Paper Award will be given for each track.
• Conference Record No