Congratulations to Dr. Chhaya Kulkarni and Dr. Anita Komlodi! Dr. Kulkarni presented their poster at the Provost’s Teaching and Learning Symposium on Friday, October 2, 2026.
Abstract
Audio deepfakes are artificial speech recordings that use machine learning algorithms to seem like actual human voices. These technologies can represent major threats such as disinformation and fraud, making deepfake detection a critical skill for computing students. Teaching audio deepfake detection is challenging. We studied whether Caselets – structured, scenario-based learning exercises – can effectively teach these concepts by drawing upon knowledge from both computer science and linguistics. We tested our approach with 53 undergraduate students in two computing courses using different teaching methods. Course A (n=29) used guided instruction with linguistic feature training, while Course B (n = 24) used collaborative interactive learning. Students completed pre- and post-class surveys measuring their self-reported knowledge and answered three open-ended questions. Students called for more practice, real-world links, interaction, linguistic focus, and research ties. Caselets effectively supported interdisciplinary learning and show promise for scaling to other computing courses.
Authors: A. Komlodi (UMBC), C. Kulkarni (Towson University), L. Neelakandan, V.P. Janeja, C. Mallinson, and L. K. Chen (UMBC)
This work is supported by NSF Award #2346473.