Paper
2 May 2024 Reversible adversarial image examples with beam search attack and grayscale invariance
Haodong Zhang, Chi Man Pun, Xia Du
Author Affiliations +
Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 1316410 (2024) https://doi.org/10.1117/12.3018262
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia
Abstract
Reversible adversarial examples (RAE) combine adversarial attacks and reversible data hiding technology on a single image to prevent illegal access. Most RAE studies focus on achieving white-box attacks. In this paper, we propose a novel framework to generate reversible adversarial examples, which combines a novel beam search based black-box attack and reversible data hiding with grayscale invariance (RDH-GI). This RAE uses beam search to evaluate the adversarial gain of historical perturbations and guide adversarial perturbations. After the adversarial examples are generated, the framework RDH-GI embeds the secret data that can be recovered losslessly. Experimental results show that our method can achieve an average peak signal-to-noise ratio (PSNR) of at least 40dB compared to source images with limited query budgets. Our method can also achieve a targeted black-box reversible adversarial attack for the first time.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Haodong Zhang, Chi Man Pun, and Xia Du "Reversible adversarial image examples with beam search attack and grayscale invariance", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 1316410 (2 May 2024); https://doi.org/10.1117/12.3018262
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
Back to Top