Wang research group presents at international AI conference

Huimin Zeng
Huimin Zeng
Dong Wang
Dong Wang, Associate Professor

Members of Associate Professor Dong Wang's research group, the Social Sensing Lab, presented their research at the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI 2022). The conference, which brings together AI researchers from around the world, was held in Vienna, Austria, from July 23-29.

PhD student Huimin Zeng presented the paper "On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks," which he coauthored with Wang. In the paper, the researchers examine the vulnerability of uncertainty estimation in AI models. For instance, in the case of an autonomous car, a malicious adversary could try to fool the car’s AI module into believing a driving situation is not ambiguous, leading the module to make an over-confident and wrong prediction in a "stop-or-proceed" situation. According to the researchers, experimental results on various benchmark image datasets show that the uncertainty estimated by state-of-the-art methods could be easily corrupted by an attack where an "outsider" wants to break into the decision process of AI models.

Informatics PhD student Zhenrui Yue presented the paper, "A Human-AI Interactive Approach Towards Natural Language Explanation based COVID-19 Misinformation Detection," which he coauthored with Wang. To identify COVID-19 misleading posts on social media, the researchers developed a human-AI framework where the reasoning ability of freelance workers on online crowdsourcing platforms is utilized along with the professional knowledge of COVID articles. They find that their framework outperforms existing misinformation detection models in both explainability and detection accuracy.  

Updated on
Backto the news archive

Related News

Spectrum Scholar Spotlight: Dalia Ortiz Pon

Twelve iSchool master's students were named 2024–2025 Spectrum Scholars by the American Library Association (ALA) Office for Diversity, Literacy, and Outreach Services. This "Spectrum Scholar Spotlight" series highlights the School's scholars. MSLIS student Dalia Ortiz Pon earned her bachelor's degree in Latina/Latino studies from San Francisco State University. 

Dalia Ortiz Pon

Debnath datafies "The Bulletin"

MSIM student Tan Debnath, whose interests span data mining, statistical modeling, text mining, and digital humanities, joined the Center for Children's books as a research assistant. He was tasked with building curation processes that would datafy seventy-five years' worth of archival issues of The Bulletin of the Center for Children's Books, one of the nation's leading children's book review journals.

Tan Debnath stands casually with his hands in his pockets and smiles broadly at the camera. It's a sunny day

He receives Amazon Research Award to improve monitoring of Earth’s ecosystem

A new project led by Professor Jingrui He aims to help scientists monitor disruptions to the Earth’s ecosystem, such as climate change. She recently received support for her work through an Amazon Research Award, which includes $60,000 in cash and an additional $40,000 in Amazon Web Services (AWS) credits.

Jingrui He

iSchool undergraduates selected as 2025 Community-Academic Scholars

The Interdisciplinary Health Sciences Institute (IHSI) has selected BSIS student Dhanvi Puttur and BSIS+DS student Lara Terpetschnig as 2025 Community-Academic Scholars. Representing nineteen majors and nine minors in eight colleges and schools at the University of Illinois Urbana-Champaign and two additional universities, the eighteen scholars in this cohort encompass diverse fields of study, from community health to graphic design to statistics. 

BSIS+DS student Lara Terpetschnig and BSIS student Dhanvi Puttur

Guan successfully defends dissertation

Doctoral candidate Yingjun Guan successfully defended his dissertation, "Disambiguating Academic Institution Names: A Comprehensive Study of Authority Files, Linguistic Variations, and Computational Evaluation in PubMed Affiliations," on April 28. 

Yingjun Guan