Text's armor: optimized local adversarial perturbation against scene text editing attacks

Xiang, Tao, Liu, Hangcheng ORCID: https://orcid.org/0000-0003-4544-3481, Guo, Shangwei, Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 and Zhang, Tianwei 2022. Text's armor: optimized local adversarial perturbation against scene text editing attacks. Presented at: Proceedings of the 30th ACM International Conference on Multimedia (MM ’22), 10-14 October 2022. Proceedings of the 30th ACM International Conference on Multimedia (MM ’22). New York: Association for Computing Machinery, pp. 2777-2785. 10.1145/3503161.3548103

Full text not available from this repository.

Abstract

Deep neural networks (DNNs) have shown their powerful capability in scene text editing (STE). With carefully designed DNNs, one can alter texts in a source image with other ones while maintaining their realistic look. However, such editing tools provide a great convenience for criminals to falsify documents or modify texts without authorization. In this paper, we propose to actively defeat text editing attacks by designing invisible "armors" for texts in the scene. We turn the adversarial vulnerability of DNN-based STE into strength and design local perturbations (i.e., "armors") specifically for texts using an optimized normalization strategy. Such local perturbations can effectively mislead STE attacks without affecting the perceptibility of scene background. To strengthen our defense capabilities, we systemically analyze and model STE attacks and provide a precise defense method to defeat attacks on different editing stages. We conduct both subjective and objective experiments to show the superior of our optimized local adversarial perturbation against state-of-the-art STE attacks. We also evaluate the portrait and landscape transferability of our perturbations.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Association for Computing Machinery
ISBN:	978-1-4503-9203-7
Last Modified:	09 Nov 2022 10:15
URI:	https://orca.cardiff.ac.uk/id/eprint/154043

Actions (repository staff only)

Edit Item