Adversarial Example Detection Based on Improved GhostBustersopen access
- Authors
- Kim, H.; Shin, J.; Jo, H.J.
- Issue Date
- Nov-2022
- Publisher
- Institute of Electronics Information Communication Engineers
- Keywords
- adversarial examples; convolutional neural network; Fourier transformation; image classification
- Citation
- IEICE Transactions on Information and Systems, v.E105D, no.11, pp.1921 - 1922
- Journal Title
- IEICE Transactions on Information and Systems
- Volume
- E105D
- Number
- 11
- Start Page
- 1921
- End Page
- 1922
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/43413
- DOI
- 10.1587/transinf.2022NGL0005
- ISSN
- 0916-8532
- Abstract
- In various studies of attacks on autonomous vehicles (AVs), a phantom attack in which advanced driver assistance system (ADAS) misclassifies a fake object created by an adversary as a real object has been proposed. In this paper, we propose F-GhostBusters, which is an improved version of GhostBusters that detects phantom attacks. The proposed model uses a new feature, i.e, frequency of images. Experimental results show that F-GhostBusters not only improves the detection performance of GhostBusters but also can complement the accuracy against adversarial examples. © 2022 The Institute of Electronics, Information and Communication Engineers.
- Files in This Item
-
Go to Link
- Appears in
Collections - College of Information Technology > School of Software > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/43413)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.