UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Conditional Adversarial Camera Model Anonymization

Andrews, JTA; Zhang, Y; Griffin, LD; (2020) Conditional Adversarial Camera Model Anonymization. In: Proceedings of the Computer Vision – ECCV 2020 Workshops 2020. (pp. pp. 217-235). Springer Nature: Cham, Switzerland. Green open access

[thumbnail of 2002.07798v3.pdf]
Preview
Text
2002.07798v3.pdf - Accepted version

Download (18MB) | Preview

Abstract

The model of camera that was used to capture a particular photographic image (model attribution) is typically inferred from high-frequency model-specific artifacts present within the image. Model anonymization is the process of transforming these artifacts such that the apparent capture model is changed. We propose a conditional adversarial approach for learning such transformations. In contrast to previous works, we cast model anonymization as the process of transforming both high and low spatial frequency information. We augment the objective with the loss from a pre-trained dual-stream model attribution classifier, which constrains the generative network to transform the full range of artifacts. Quantitative comparisons demonstrate the efficacy of our framework in a restrictive non-interactive black-box setting.

Type: Proceedings paper
Title: Conditional Adversarial Camera Model Anonymization
Event: Computer Vision – ECCV 2020 Workshops
ISBN-13: 9783030668228
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-66823-5_13
Publisher version: https://doi.org/10.1007/978-3-030-66823-5_13
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Camera model anonymization, Conditional generative adversarial nets, Adversarial training, Non-interactive black-box attacks, Image editing/manipulation, Camera model attribution/identification,
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10120869
Downloads since deposit
16Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item