Citation

Ng, Koi Yee and Ong, Simying and Loh, Yuen Peng (2023) Can StArtGAN withstand Image Processing Attacks? In: 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 31 Oct - 3 Nov 2023, Taipei, Taiwan.

Text 8.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

StArtGAN is a constructive-based coverless data hiding framework, that generates various classes of art images to represent secret bits. These generated art images will be collated to form a collage image that carries the secret data. In certain data hiding applications such as watermarking applications, robustness is an important factor to be considered in such a data hiding framework. Therefore, in this paper, we will investigate the robustness level of StArtGAN. Six common image processing operations with multiple variants are applied as the robustness attacks to the collage image output from StArtGAN to examine its classification accuracy (or secret data extraction accuracy) and its perceptual qualities after these attacks. The result proves that this framework is robust to Salt & Pepper Noise, Gaussian Noise, Sharpening, Gaussian Filter, and Compression Attacks.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Image coding
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	02 Jan 2024 07:28
Last Modified:	02 Jan 2024 07:28
URII:	http://shdl.mmu.edu.my/id/eprint/11966

Downloads

Edit (login required)