Research Overview
Drs. Atul Prakash (Computer Science and Engineering) and Huei Peng (Mechanical Engineering) aim to improve the robustness of machine learning models by taking advantage of environmental context, particular laws of physics and semantic background information. This new approach to machine learning can lead to reduced training needs and more robust learning even with significant perturbations.
Research Impact
Research Team
Dr. Atul Prakash, Computer Science and Engineering Division, University of Michigan, Ann Arbor
Dr. Huei Peng, Department of Mechanical Engineering, University of Michigan, Ann Arbor
Research Highlights
Recent Publications
-
Efficient Adversarial Training with Transferable Adversarial Examples
(CVPR 2020 publication on a fast adversarial training method called ATTA)
Code release for ATTA -
Robust Physical Hard-Label Attacks on Deep Learning Visual Classification
This team has also received an NSF grant.
