(734)763-1585

Applications:
Computer Science, Cyber Security, Information Systems, Networks, Sensors and Sensor Networks
Methodologies:
Classification, Data Security and Privacy, Deep Learning, Optimization
Relevant Projects:

IoT/CPS Security Research at the University of Michigan


Connections:

Data Science Undergraduate Program Advisor and PC member

Atul Prakash

Professor

EECS, College of Engineering

My research interests include security, privacy, and adversarial machine learning.
More information about some of the current projects can be found at https://iotsecurity.engin.umich.edu.

An adversarial testing pipeline to fool machine learning classifiers. A STOP sign is being modified using stickers so that a state-of-the-art classifier is fooled into thinking it is a 45 SPEED LIMIT sign. For more details, visit https://iotsecurity.engin.umich.edu (Robust Physical Perturbations tab)