Supriyo Chakraborty is a research staff member in the Distributed Cognitive Systems group at the IBM T. J. Watson Research Center since 2014. His research interests are geared towards a principled understanding of the emerging concerns of trust and privacy that arise during information sharing and to develop formalisms, algorithms and system mechanims to effectively address them. Specifically, he has made contributions in the areas of designing inference-driven privacy algorithms for sensor data, applied cryptography, side-channel attacks, trust management, and uncertainty modeling for effective decision-making.
More recently his work has focused on different aspects of adversarial machine learning including evasion and poisoning attacks in black box settings, and on interpretability of deep learning models.
Prior to this he obtained his Ph.D. in Electrical Engineering from the University of California, Los Angeles in 2014, and a Masters degree also in Electrical Engineering from the Indian Institute of Technology, Bombay in 2006. He is the recipient of the Intel Student Programming Contest award, Henry Samueli Fellowship and Dissertation Year Fellowship at UCLA, and the Qualcomm Innovation Fellowship (2011).
Dr. Chakraborty also serves on the technical program committee (TPC) of top machine learning conferences including NeurIPS, ICML, AAAI, and IJCAI and as a reviewer for a number of international journals and conferences.
For a list of his patents please visit: https://patents.google.com/?inventor=Supriyo+Chakraborty