Secure, Low Power and Reliable Implementations of Deep Learning
A talk by Prof. Siddharth Garg, New York University/Tandon School of Engineering
TU Wien, Campus Gußhaus
EI 4 Reithoffer-Hörsaal
1040 Vienna, Gußhausstraße 25
Stiege 8, 2. Stock, Raum CF0245
This talk will provide an overview of the research activities in my group on secure, reliable and energy-efficient implementations of deep neural networks. The first part of the talk will highlight emerging security vulnerabilities in deep learning, specifically, on how deep learning models can be “backdoored” via training data poisoning. Backdoored Neural Networks (or BadNets) behave normally on validation data but misbehave on certain backdoored inputs, for example, stop signs with PostIt notes stuck on them. The second part of the talk will highlight our work on robust and energy-efficient hardware implementations for deep neural network based inference. We will show how the power consumption of Google TPU like architectures can be cut in half without impacting performance or accuracy.
About Siddharth Garg
Siddharth Garg received his Ph.D. degree in Electrical and Computer Engineering from Carnegie Mellon University in 2009, and a B.Tech. degree in Electrical Enginerring from the Indian Institute of Technology Madras. He joined NYU in Fall 2014 as an Assistant Professor, and prior to that, was an Assistant Professor at the University of Waterloo from 2010-2014. His general research interests are in computer engineering, and more particularly in secure, reliable and energy-efficient computing.
In 2016, Siddharth was listed in Popular Science Magazine’s annual list of “Brilliant 10” researchers. Siddharth has received the NSF CAREER Award (2015), and paper awards at the IEEE Symposium on Security and Privacy (S&P) 2016, USENIX Security Symposium 2013, at the Semiconductor Research Consortium TECHCON in 2010, and the International Symposium on Quality in Electronic Design (ISQED) in 2009. Siddharth also received the Angel G. Jordan Award from ECE department of Carnegie Mellon University for outstanding thesis contributions and service to the community. He serves on the technical program committee of several top conferences in the area of computer engineering and computer hardware, and has served as a reviewer for several IEEE and ACM journals.
Information for Students
The lecture series on research talks by the visiting professors of the PhD School can also be credited as an elective course for students of Master’s programs of Informatics. More information.
- Prof. Siddharth Garg, New York University/Tandon School of Engineering
Note: This is one of the thousands of items we imported from the old website. We’re in the process of reviewing each and every one, but if you notice something strange about this particular one, please let us know. — Thanks!