EKILA: Synthetic Media Provenance and Attribution for Generative Art

Kar Balan; Shruti Agarwal; Simon Jenni; Andy Parsons; Andrew Gilbert; John Philip Collomosse

doi:10.1109/CVPRW59228.2023.00098

Back

EKILA: Synthetic Media Provenance and Attribution for Generative Art

Conference proceeding

Open access

EKILA: Synthetic Media Provenance and Attribution for Generative Art

Kar Balan, Shruti Agarwal, Simon Jenni, Andy Parsons, Andrew Gilbert and John Philip Collomosse

Proceedings of the 2023 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023)

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023) (Vancouver, Canada and online, 17/06/2023 - 24/06/2023)

14/08/2023

DOI: https://doi.org/10.1109/CVPRW59228.2023.00098

Abstract

Training

Visualization

Correlation

Training data

Prototypes

Data models

Ecosystems

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.

Files and links (2)

pdf

Balan_EKILA_Synthetic_Media_Provenance_and_Attribution_for_Generative_Art_CVPRW_2023_paper3.24 MBDownload View

Author's Accepted Manuscript Open Access

url

https://doi.org/10.1109/CVPRW59228.2023.00098View

Metrics

69 File views/ downloads

18 Record Views

Details

Title: EKILA: Synthetic Media Provenance and Attribution for Generative Art
Creators: Kar Balan (Author) - University of Surrey, School of Computer Science and Electronic Engineering
Shruti Agarwal (Author) - Adobe Systems
Simon Jenni (Author) - Adobe Systems
Andy Parsons (Author) - Adobe Systems
Andrew Gilbert (Author) - University of Surrey, Department of Music and Media
John Philip Collomosse (Author) - University of Surrey, School of Computer Science and Electronic Engineering
Publication Details: Proceedings of the 2023 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023)
Conference: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2023) (Vancouver, Canada and online, 17/06/2023 - 24/06/2023)
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date accepted: 27/02/2023
Grants: EP/T022485/1, Engineering and Physical Sciences Research Council (United Kingdom, Swindon) - EPSRC
Grant note: Implementation of the EKILA prototype was supported in part by DECaDE under EPSRC Grant EP/T022485/1.
Identifiers: 99778665402346
Copyright: © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Academic Unit: Department of Music and Media; School of Computer Science and Electronic Engineering
Language: English
Resource Type: Conference proceeding

EKILA: Synthetic Media Provenance and Attribution for Generative Art

Abstract

Files and links (2)

Metrics

Details

Usage Policy