Adversarial Example Generation Method for Vehicle Environment Perception System

被引：0

作者：

Huang S. ^{[1
]}

Zhang Z. ^{[2
]}

Dong D. ^{[1
]}

Qin J. ^{[2
]}

机构：

[1] Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Shanghai

[2] Key Laboratory of Road and Traffic Engineering, the Ministry of Education, Tongji University, Shanghai

来源：

Tongji Daxue Xuebao/Journal of Tongji University | 2022年 / 50卷 / 10期

关键词：

adversarial attack; deep learning; object detection; vehicle environment perception system; white-box attack;

D O I：

10.11908/j.issn.0253-374x.22227

中图分类号：

学科分类号：

摘要：

A method of generating adversarial examples against object detectors was proposed for object detection system in vehicle environment perception scenarios. The method achieves white-box adversarial attacks on object detectors，i.e.，object invisible attacks and object targeted mis-detectable attacks. On the Rail dataset and Cityscapes dataset，experimental results indicate that the method has good performance on the object invisible attacks and the object targeted mis-detectable attacks in the process of YOLO object detection. © 2022 Science Press. All rights reserved.

引用

页码：1377 / 1384

页数：7

共 27 条

[1]

Shize HUANG, Yachan ZHAI, Miaomiao ZHANG, Et al., Arc detection and recognition in pantograph-catenary system based on convolutional neural network ［J］, Information Sciences, 501, (2019)

[2]

HUANG Shize, YANG Lingyu, TAO Ting, Et al., A method of tram obstacle intrusion detection and track recognition based on instance segmentation［J］, Shanghai Highways, 2, (2021)

[3]

HUANG Shize, CHEN Wei, ZHANG Fan, Et al., Method of turnout fault diagnosis based on Fréchet distance［J］, Journal of Tongji University（Natural Science）, 46, 12, (2018)

[4]

Ting TAO, Decun DONG, Shize HUANG, Et al., Gap detection of switch machines in complex environment based on object detection and image processing ［J］, Journal of Transportation Engineering，Part A：Systems, 146, 8, (2020)

[5]

Shize HUANG, Lingyu YANG, Fan ZHANG, Et al., Turnout fault diagnosis based on CNNs with self-generated samples［J］, Journal of Transportation Engineering，Part A：Systems, 146, 9, (2020)

[6]

SUTSKEVER I，, Et al., Intriguing properties of neural networks［J/OL］

[7]

MOOSAVI-DEZFOOLI S M, FROSSARD P., DeepFool：a simple and accurate method to fool deep neural networks ［C］, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574-2582, (2016)

[8]

SZEGEDY C., Explaining and harnessing adversarial examples［J/OL］

[9]

PAPERNOT N，, MCDANIEL P，, JHA S，, Et al., The limitations of deep learning in adversarial settings ［C］, Proceedings of 2016 IEEE European Symposium on Security and Privacy （EuroS&P）, pp. 372-387, (2016)

[10]

CAELINI N，, WAGNER D., Towards evaluating the robustness of neural networks, Processing of the 2017 IEEE Symposium on Security and Privacy （SP）, pp. 39-57, (2017)

← 1 2 3 →