The search functionality is under construction.
The search functionality is under construction.

Adversarial Example Detection Based on Improved GhostBusters

Hyunghoon KIM, Jiwoo SHIN, Hyo Jin JO

  • Full Text Views

    0

  • Cite this

Summary :

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.

Publication
IEICE TRANSACTIONS on Information Vol.E105-D No.11 pp.1921-1922
Publication Date
2022/11/01
Publicized
2022/04/19
Online ISSN
1745-1361
DOI
10.1587/transinf.2022NGL0005
Type of Manuscript
Special Section LETTER (Special Section on Next-generation Security Applications and Practice)
Category

Authors

Hyunghoon KIM
  Soongsil University
Jiwoo SHIN
  Soongsil University
Hyo Jin JO
  Soongsil University

Keyword