Wu gave a presentation in DART Webinar!

Towards Robust Machine Learning under Distribution Shift and Adversarial Attack

Presenter(s): Xintao Wu
Date: October 27, 2021

As big data and AI technologies are deployed to make critical decisions that potentially affect individuals (e.g., employment, college admissions, credit, and health insurance), there are increasing concerns from the public on privacy, fairness, safety, and robustness issues of data analytics, collection, sharing and decision making. In this talk, we first overview our social awareness research, in particular, on how to mitigate side effect of enforcing one social concern on another, and how to address multiple social concerns simultaneously. We then focus on robustness of machine learning under two representative scenarios, distribution shift and adversarial attack. In the former scenario, we present robust learning based on kernel reweighing and Heckman model. In the second scenario, we present adaptive defense that purposely leverages multiple types of adversarial samples to learn the context information in the training. We conclude the talk with some future research directions.

The Arkansas NSF EPSCoR program is a multi-institutional, interdisciplinary, statewide grant program leveraging $24 million over 5 years to expand research, workforce development, and science, technology, engineering, and mathematics (STEM) educational outreach in Arkansas. The program is administered by the Arkansas Economic Development Commission (AEDC) Division of Science and Technology to maximize resources available to support the advancement of STEM in Arkansas.

The new Track 1 project, Data Analytics that are Robust and Trusted (DART), was awarded July 1, 2020 and will fund five years of cutting-edge data science research and education around the state.