EKILA: Synthetic Media Provenance and Attribution for Generative Art

Kar Balan [1], Pranav Agarwal [2], Simon Jenni [2], Andy Parsons [2], Andrew Gilbert [1], John Collomosse [2]. 
[1] University of Surrey,  [2] Adobe Research
​In The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 Workshop
Workshop of Media Forensics 2023

Abstract

 We present EKILA; a decentralized framework that enables creatives to receive recognition and reward for their contributions to generative AI (GenAI).  EKILA proposes a robust visual attribution technique and combines this with an emerging content provenance standard (C2PA) to address the problem of synthetic image provenance -- determining the generative model and training data responsible for an AI-generated image.  Furthermore, EKILA extends the non-fungible token (NFT) ecosystem to introduce a tokenized representation for rights, enabling a triangular relationship between the asset's Ownership, Rights, and Attribution (ORA). Leveraging the ORA relationship enables creators to express agency over training consent and, through our attribution model, to receive apportioned credit, including royalty payments for the use of their assets in GenAI.

Paper

EKILA: Synthetic Media Provenance and Attribution for Generative Art, Kar Balan, Pranav Agarwal, Simon Jenni, Andy Parsons, Andrew Gilbert, John Collomosse. In Proc CVPR'23WS 2023

Poster

​Citation

@inproceedings{Balan:CVPRWS:2023,
AUTHOR = Balan Kar and Agarwal Pranav and Jenni Simon  and Parsons Andy and  Gilbert Andrew and Collomosse, John",
TITLE = "EKILA: Synthetic Media Provenance and Attribution for Generative Art",
BOOKTITLE = "CVPR'23WS 2023: Media Forensics Workshop",
YEAR = "2023",
​}