Wang research group presents at international AI conference

Huimin Zeng
Huimin Zeng
Zhenrui Yue
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

Final projects in Government Information course result in publications

Two students who were enrolled in the Government Information (IS 594) course this past spring are now published authors. Their papers began as their final project for the course, which acquaints students with government publications. With the students' permission, course instructor and Adjunct Lecturer Dominique Hallett submitted the papers to DttP: Documents to the People, and they were published in the journal's most recent edition (Vol. 51, No. 3).

Internship Spotlight: AbbVie

BSIS student Miranda Ma discusses her internship at the AbbVie Innovation Center. Ma advises job seekers to keep an open mind and not limit their job search to a specific industry, especially for a field like user experience.

Miranda Ma

Tilley shares comics research at European universities

Associate Professor Carol Tilley shared her expertise in comics research at several invited talks in Europe this month. Tilley served as the keynote speaker for the international conference, “Comics, the Children and Childishness,” at Ghent University in Belgium. In her keynote, “Re-Centering Children in Comics,” she encouraged researchers studying comics and children to give more focus to the lived experiences of young people, moving away from an over-reliance on studying specific texts or their uses. 

Carol Tilley

Knox testifies before U.S. Senate Judiciary Committee on book bans

Associate Professor Emily Knox testified before the U.S. Senate Committee on the Judiciary on September 12. She was one of five witnesses offering testimony for the hearing "Book Bans: Examining How Censorship Limits Liberty and Literature." 

Emily Knox

McDowell examines benefits and obstacles of library data storytelling

The effective use of data storytelling could positively impact public library managers' approaches to data collection and their advocacy for libraries, according to Associate Professor Kate McDowell. However, cultural roadblocks to data storytelling must be addressed for the process to be successful, McDowell discovered in a recently completed study.

Kate McDowell