Weekly AIR Seminar 02/12

Speaker: Keanu Nichols, PhD Student at Boston University (CAS)

Talk Title: Multi-domain Analysis and Generalization of Image manipulation loCalization

Abstract: Advanced image editing software enables easy creation of highly convincing image manipulations, which has been made even more accessible in recent years due to advances in generative AI. Manipulated images, while often harmless, could spread misinformation, create false narratives, and influence people's opinions on important issues. Despite this growing threat, current research on detecting advanced manipulations across different visual domains, remains limited. Thus, we introduce Multi-domain Analysis and Generalization of Image manipulation loCalization (MAGIC), a comprehensive benchmark designed for studying generalization across several axes in image manipulation detection. MAGIC comprises over 192K images from two distinct sources (user and news photos), spanning a diverse range of topics and manipulation sizes. We focus on images manipulated using recent diffusion-based inpainting methods, which are largely absent in existing datasets. We conduct experiments under different types of domain shift to evaluate robustness of existing image manipulation detection methods. Our goal is to drive further research in this area by offering new insights that would help develop more reliable and generalizable image manipulation detection methods.

Bio: Keanu Nichols joined the Image and Video Computing group as a PhD student in 2023. He received his Master's in AI at BU. He is advised by Professor Bryan Plummer. His primary research interests lie in applications of machine learning in vision. Currently he is working on tasks such as image manipulation detection and 3D Spatial Orientation.

Back to Calendar