ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION

Hong Joo Lee; Yong Man Ro

doi:10.1109/ICIP42928.2021.9506748

ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION

Hong Joo Lee
, Yong Man Ro

Dept. of Applied Artificial Intelligence

Korea Advanced Institute of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Multi-sensor data fusion model aims to improve the model performance by fusing multiple types of sensor data. Although multi-sensor data fusion models have been developed for remarkable performance, there is a lack of studies on the adversarial vulnerability of the multi-sensor data fusion models. In this paper, we propose a robust multi-sensor data fusion method that is not vulnerable to adversarial attacks. To this end, we devise a random feature fusion method to preserve multi-sensor fusion features. Through the random feature fusion, we could explicitly hide the information about which features are being used for the fusion. In experiments, we verify that our proposed random feature fusion method shows the adversarial robustness considerably under diverse adversarial settings.

Original language	English
Title of host publication	2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
Publisher	IEEE Computer Society
Pages	339-343
Number of pages	5
ISBN (Electronic)	9781665441155
DOIs	https://doi.org/10.1109/ICIP42928.2021.9506748
State	Published - 2021
Event	28th IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States Duration: 19 Sep 2021 → 22 Sep 2021

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2021-September
ISSN (Print)	1522-4880

Conference

Conference	28th IEEE International Conference on Image Processing, ICIP 2021
Country/Territory	United States
City	Anchorage
Period	19/09/21 → 22/09/21

Keywords

Adversarial robustness
Multi-sensor data fusion
Random feature fusion

Access to Document

10.1109/ICIP42928.2021.9506748

Cite this

Lee, H. J., & Ro, Y. M. (2021). ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION. In 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings (pp. 339-343). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2021-September). IEEE Computer Society. https://doi.org/10.1109/ICIP42928.2021.9506748

@inproceedings{657cdb5b008a4463b9fcd413ee14d21a,

title = "ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION",

abstract = "Multi-sensor data fusion model aims to improve the model performance by fusing multiple types of sensor data. Although multi-sensor data fusion models have been developed for remarkable performance, there is a lack of studies on the adversarial vulnerability of the multi-sensor data fusion models. In this paper, we propose a robust multi-sensor data fusion method that is not vulnerable to adversarial attacks. To this end, we devise a random feature fusion method to preserve multi-sensor fusion features. Through the random feature fusion, we could explicitly hide the information about which features are being used for the fusion. In experiments, we verify that our proposed random feature fusion method shows the adversarial robustness considerably under diverse adversarial settings.",

keywords = "Adversarial robustness, Multi-sensor data fusion, Random feature fusion",

author = "Lee, \{Hong Joo\} and Ro, \{Yong Man\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 28th IEEE International Conference on Image Processing, ICIP 2021 ; Conference date: 19-09-2021 Through 22-09-2021",

year = "2021",

doi = "10.1109/ICIP42928.2021.9506748",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "339--343",

booktitle = "2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings",

}

Lee, HJ & Ro, YM 2021, ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION. in 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2021-September, IEEE Computer Society, pp. 339-343, 28th IEEE International Conference on Image Processing, ICIP 2021, Anchorage, United States, 19/09/21. https://doi.org/10.1109/ICIP42928.2021.9506748

ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION. / Lee, Hong Joo; Ro, Yong Man.
2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. IEEE Computer Society, 2021. p. 339-343 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2021-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION

AU - Lee, Hong Joo

AU - Ro, Yong Man

PY - 2021

Y1 - 2021

N2 - Multi-sensor data fusion model aims to improve the model performance by fusing multiple types of sensor data. Although multi-sensor data fusion models have been developed for remarkable performance, there is a lack of studies on the adversarial vulnerability of the multi-sensor data fusion models. In this paper, we propose a robust multi-sensor data fusion method that is not vulnerable to adversarial attacks. To this end, we devise a random feature fusion method to preserve multi-sensor fusion features. Through the random feature fusion, we could explicitly hide the information about which features are being used for the fusion. In experiments, we verify that our proposed random feature fusion method shows the adversarial robustness considerably under diverse adversarial settings.

AB - Multi-sensor data fusion model aims to improve the model performance by fusing multiple types of sensor data. Although multi-sensor data fusion models have been developed for remarkable performance, there is a lack of studies on the adversarial vulnerability of the multi-sensor data fusion models. In this paper, we propose a robust multi-sensor data fusion method that is not vulnerable to adversarial attacks. To this end, we devise a random feature fusion method to preserve multi-sensor fusion features. Through the random feature fusion, we could explicitly hide the information about which features are being used for the fusion. In experiments, we verify that our proposed random feature fusion method shows the adversarial robustness considerably under diverse adversarial settings.

KW - Adversarial robustness

KW - Multi-sensor data fusion

KW - Random feature fusion

UR - https://www.scopus.com/pages/publications/85125587469

U2 - 10.1109/ICIP42928.2021.9506748

DO - 10.1109/ICIP42928.2021.9506748

M3 - Conference contribution

AN - SCOPUS:85125587469

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 339

EP - 343

BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings

PB - IEEE Computer Society

T2 - 28th IEEE International Conference on Image Processing, ICIP 2021

Y2 - 19 September 2021 through 22 September 2021

ER -

ADVERSARIALLY ROBUST MULTI-SENSOR FUSION MODEL TRAINING VIA RANDOM FEATURE FUSION FOR SEMANTIC SEGMENTATION

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this