Adversarial Neural Pruning with Modified Latent Vulnerability utilizing Feature Robustness
- Authors
- Lim, Hyuntak; Chung, Ki Seok
- Issue Date
- Nov-2021
- Publisher
- IEEE
- Keywords
- Adversarial Attack; Weight Pruning
- Citation
- 2021 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2021, pp.1 - 4
- Indexed
- SCOPUS
- Journal Title
- 2021 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2021
- Start Page
- 1
- End Page
- 4
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/140381
- DOI
- 10.1109/ICCE-Asia53811.2021.9641893
- Abstract
- Today, vision recognition with Convolutional Neural Network (CNN) shows performance good enough to be employed in safety-critical autonomous driving. However, CNN models are vulnerable to adversarial attacks. To overcome this vulnerability, many methods have been studied Pruning is regarded as one of the effective methods to make the network more robust against adversarial attacks. In this paper, we introduce a new vulnerability loss to suppress the vulnerability better when the pruning is used to counter adversarial attacks. With this vulnerability suppression, we achieve up to 1.12% better accuracy against the adversarial examples compared to a previous study called ANP-VS.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.