Trustworthy AI Symposium

Dates: October 30 - November 1 (Wednesday- Friday) 2.5 days

Location: Columbia University | Location TBD

 

Recent years have seen an astounding growth in deployment of AI systems in critical domains such as autonomous vehicles, criminal justice, healthcare, hiring, housing, human resource management, law enforcement, and public safety, where decisions taken by AI agents directly impact human lives. Consequently, there is an increasing concern if these decisions can be trusted to be correct, reliable, fair, and safe, especially under adversarial attacks.

 

Under the umbrella of trustworthy computing, there is a long-established framework employing formal methods and verification techniques for ensuring trust properties like reliability, security, and privacy of traditional software and hardware systems.  Just as for trustworthy computing, formal verification could be an effective approach for building trust in AI-based systems. However, the set of properties needs to be extended beyond reliability, security, and privacy to include fairness, robustness, probabilistic accuracy under uncertainty, and other properties yet to be identified and defined. Further, there is a need for new property specifications and verification techniques to handle new kinds of artifacts, e.g., data distributions, probabilistic programs, and machine learning based models that may learn and adapt automatically over time.

 

This first Trustworthy AI Symposium aims to bring together researchers from the trustworthy computing and artificial intelligence communities, along with researchers and practitioners utilizing AI methods in a variety of domains, to explore the future of trust, fairness, privacy, and robustness in AI-based systems. Through a mix of lightning talks and tutorial-style talks, interspersed with break-out sessions for exploring new interdisciplinary research directions, we hope to lay down the seeds of a long-term research agenda for the whole computing community. Our goal is to give reason for people, communities, and society to trust the computing systems we build, now and for the future. The symposium, which is by invitation only, is sponsored by Capital One, a DSI Industry Affiliate.


Participants:

  • Elias Barenboim, Associate Professor of Computer Science and Data Science Institute, Columbia University
  • Brian Barr, Machine Learning Researcher, Capital One
    Karen Bhatia, Senior Vice President, Tech, NYCEDC
  • David Blei, Professor of Statistics and Computer Science and Data Science Institute, Columbia University
  • Nicholas Carlini, Research Scientist, Google Brain
  • Elisa CelisAssistant Professor of Statistics and Data Science, Yale University
  • Kamalika Chaudhuri, Associate Professor of Computer Science and Engineering, UC San Diego 
  • Bo Cowgill, Assistant Professor of Business and Data Science Institute, Columbia University
  • Rachel Cummings: Assistant Professor in the H. Milton Stewart School of Industrial and Systems Engineering, Georgia Tech
  • Anupam Datta: Professor of Electrical and Computer Engineering and (by courtesy) Computer Science, Carnegie Mellon University
  • Laurent El Ghaoui, Professor, EECS and IEOR Departments, UC Berkeley
  • Ulfar Erlingsson, Research Scientist, Google Brain
  • Golnoosh Farnadi, Postdoctoral fellow, Polytechnique Montréal
  • Ronghui Gu, Assistant Professor of Computer Science and Data Science Institute, Columbia University
  • Mark Hansen, Professor of Journalism and Data Science Institute, Columbia University
  • Keegan Hines, Director of Machine Learning Research, Capital One
  • Daniel Hsu, Associate Professor of Computer Science and Data Science Institute, Columbia University
  • Lily Hu, PhD Candidate in Applied Mathematics, Harvard University and Fellow at the Berkman Klein Center for Internet and Society
  • Somesh Jha, Professor of Computer Science, UW-Madison
  • Pushmeet Kohli, Computer Scientist, Google DeepMind
  • Aleksandra Korolova, Assistant Professor of Computing Science at USC
  • Marta Kwiatkowska: Professor of Computing Systems, Fellow, Trinity College, University of Oxford
  • Himabindu Lakkaraju, Postdoctoral Fellow, Harvard
  • Aleksander Madry, NBX Career Development Associate Professor of Computer Science, MIT
  • Brad Martin, Senior Researcher, National Security Agency
  • Aleksandra (Saska) Mojsilovic, IBM Fellow, AI Science, Thomas J. Watson Research Center
  • Nicolas Papernot, Assistant Professor, University of Toronto and Vector Institute  
  • Desmond Patton, Associate Professor of Social Work and Data Science Institute, Columbia University
  • Claudia Perlich, Senior Data Scientist, Two Sigma 
  • Andre Platzer, Associate Professor of Computer Science, Carnegie Mellon University
  • Frida Polli, CEO and co-founder of pymetrics
  • Sriram Rajamani, Distinguished Scientist and Managing Director of Microsoft Research India
  • Aaron Roth, Associate Professor of Computer and Information Science, University of Pennsylvania
  • Sanjit Seshia, Professor, Department of Electrical Engineering and Computer Sciences, UC Berkeley
  • Eric Talley, Isidor and Seville Sulzbacher Professor of Law and Data Science Institute, Columbia University
  • Kunal Talwar, Research Scientist, Google Brain
  • Carl Vondrick, Assistant Professor of Computer Science and Data Science Institute, Columbia University
  • Eugene Wu, Assistant Professor of Computer Science and Data Science Institute, Columbia University
  • Bin Yu, Chancellor's Professor, Departments of Statistics and Electrial Engineering & Computer Sciences at UC Berkeley
  • Aleksandar Zeljic, Postdoctoral Research Fellow, Computer Science, Stanford

Steering Committee:

  • Shipra Agrawal, Assistant Professor of Industrial Engineering & Operations Research and Data Science Institute, Columbia University (co-chair)
  • Augustin Chaintreau, Assistant Professor of Computer Science and Data Science Institute, Columbia University
  • Roxana Geambasu, Associate Professor of Computer Science and Data Science Institute, Columbia University
  • Suman Jana, Assistant Professor of Computer Science and Data Science Institute, Columbia University
  • Cathryn Posey, Senior Technology Director, Machine Learning, Capital One
  • Jeannette M. Wing, Avanessians Director of the Data Science Institute and Professor of Computer Science, Columbia University (co-chair)

For further details contact Jessica B. Rodriguez, Manager of Events and Special Programs at the Data Science Institute: 212-853-1787 or jr3056@columbia.edu.  



550 W. 120th St., Northwest Corner 1401, New York, NY 10027    212-854-5660
©2018 Columbia University