Home > Seminars > Taeho Jung - Secure Computation for Distributed Deep Learning

Taeho Jung - Secure Computation for Distributed Deep Learning


9/21/2017 at 3:30PM


9/21/2017 at 4:45PM


140 DeBartolo


College of Engineering close button

Taeho Jung

Taeho Jung

VIEW FULL PROFILE Email: tjung@nd.edu
Phone: 574-631-8322
Website: https://sites.nd.edu/taeho-jung/
Office: 351 Fitzpatrick Hall


College of Engineering Assistant Professor
Big data security, user privacy, privacy-preserving computation, accountability
Click for more information about Taeho
Add to calendar:
iCal vCal

Since the victory of AlphaGo, artificial intelligence is coming to our daily life gradually, and it already started to change our life. The main breakthrough made this possible was the deep learning in conjunction with the powerful computing resources for processing big data. Though powerful it is, the way this tool is currently utilized may severely impact individual privacy owing to the sensitive information hidden in the big data. In this talk, I will briefly explain how deep learning is different from many other machine learning technologies, why it became such an important tool 30 years after the term was first used. Then, I will present how individual privacy is impacted by the current practice of utilizing this tool, and then I will proceed to the brief survey of existing fields of study in applied cryptography. Finally, I will present my achievement which will contribute to the construction of secure distributed deep learning.

Seminar Speaker:

Taeho Jung

Taeho Jung

University of Notre Dame

Taeho Jung, Ph.D. is an Assistant Professor in the Department of Computer Science and Engineering at the University of Notre Dame. He received his Ph.D. from Illinois Institute of Technology in Chicago and B.E. from Tsinghua University in Beijing. His research interests include data security, user privacy, privacy-preserving computation, and applied cryptography. Professor Jung has been exploring the security and privacy issues in data mining and provisioning in the big data life cycle.