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.
Hyunghoon KIM
Soongsil University
Jiwoo SHIN
Soongsil University
Hyo Jin JO
Soongsil University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hyunghoon KIM, Jiwoo SHIN, Hyo Jin JO, "Adversarial Example Detection Based on Improved GhostBusters" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 11, pp. 1921-1922, November 2022, doi: 10.1587/transinf.2022NGL0005.
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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022NGL0005/_p
Copy
@ARTICLE{e105-d_11_1921,
author={Hyunghoon KIM, Jiwoo SHIN, Hyo Jin JO, },
journal={IEICE TRANSACTIONS on Information},
title={Adversarial Example Detection Based on Improved GhostBusters},
year={2022},
volume={E105-D},
number={11},
pages={1921-1922},
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.},
keywords={},
doi={10.1587/transinf.2022NGL0005},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Adversarial Example Detection Based on Improved GhostBusters
T2 - IEICE TRANSACTIONS on Information
SP - 1921
EP - 1922
AU - Hyunghoon KIM
AU - Jiwoo SHIN
AU - Hyo Jin JO
PY - 2022
DO - 10.1587/transinf.2022NGL0005
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2022
AB - 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.
ER -