Two-Stage Image Restoration: A Shield against Adversarial Attacks on Face Identification
- Authors
- Lim, Min Young; Min Hong, Pyo; Lee, Youn Kyu
- Issue Date
- 2023
- Publisher
- IEEE Computer Society
- Keywords
- deep learning; defense against adversarial attacks; face identification; image restoration
- Citation
- International Conference on ICT Convergence, pp 1283 - 1285
- Pages
- 3
- Journal Title
- International Conference on ICT Convergence
- Start Page
- 1283
- End Page
- 1285
- URI
- https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/32724
- DOI
- 10.1109/ICTC58733.2023.10393701
- ISSN
- 2162-1233
- Abstract
- Various methods have been proposed to defend face identification systems against adversarial attacks by eliminating adversarial perturbations from target face images. However, it is challenging to eliminate such perturbations while preserving the crucial facial features within the images. In this paper, we propose a novel purification method for an effective defense against adversarial attacks on target face images. Our method incorporates a two-stage image restoration utilizing diffusion, consisting of sequential super-resolution-based image restoration followed by colorization-based image restoration. The experimental results demonstrate the effectiveness of our method in eliminating perturbations while preserving the identity of the facial features. © 2023 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Computer Engineering > Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.