AI-Generated Images as an Emergent Record Format
Publication Date
1-1-2023
Document Type
Conference Proceeding
Publication Title
Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023
DOI
10.1109/BigData59044.2023.10386946
First Page
2020
Last Page
2031
Abstract
AI-generated Images are disrupting existing approaches to verifying the trustworthiness of visual media. The application of generative AI in fields in which images are trusted visual evidence of persons, actions and events is drawing the attention of archival scientists and AI researchers. A literature review of AI-generated images as an emergent record format, identified an absence of archival and recordkeeping knowledge. Analysis of the results revealed six thematic categories: authenticity and verifiability; manipulation and misinformation; bias and representation; attribution and intellectual property; transparency and explainability; and ethical considerations. These themes inform the development of research questions and the next phase of the study that includes the application of theory and methods of archival diplomatics and computational archival science.
Funding Sponsor
University of British Columbia
Keywords
AI-generated images, Archives, Born-digital images, Computational Archival Science, Generative-AI, Recordkeeping
Department
Information
Recommended Citation
Jessica Bushey. "AI-Generated Images as an Emergent Record Format" Proceedings - 2023 IEEE International Conference on Big Data, BigData 2023 (2023): 2020-2031. https://doi.org/10.1109/BigData59044.2023.10386946
