The Department of Homeland Security has awarded Associate Professor Jingrui He a two-year, $319,568 grant to study how the risk of foreign influence on news media can be mitigated. Her project, "Towards a Computational Framework for Disinformation Trinity: Heterogeneity, Generation, and Explanation," will lead to a new suite of algorithms and software tools to detect, predict, generate, and understand disinformation dissemination. Hanghang Tong, associate professor of computer science at Illinois, will serve as co-principal investigator.
"As the 2020 decade unfolds, there is great optimism on what technology will emerge and how it can make daily life easier. However, the greater the technology, the greater risk foreign influence can have on that technology," He said.
For her project, He will study foreign influence via the lens of disinformation on news media from a computational perspective. She will use Explainable Heterogeneous Adversarial Machine Learning (EXHALE) to address the limitations of current techniques in terms of comprehension, characterization, and explainability.
"The proposed techniques are expected to advance state-of-the-art in machine learning and AI. They are also expected to enhance the national resilience to foreign influence operations from multiple aspects, and thus help to mitigate the risk of foreign influence through the identification of messaging, tactics, target audience, and outreach," she said.
He's research focuses on heterogeneous machine learning, rare category analysis, active learning and semi-supervised learning, with applications in social network analysis, healthcare, finance, and manufacturing processes. She earned her PhD in machine learning from Carnegie Mellon University.