Black-box Adversarial Attacks on Monocular Depth Estimation Using Evolutionary Multi-objective Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Daimo, Renya, Ono, Satoshi, Suzuki, Takahiro
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910516361822208
author Daimo, Renya
Ono, Satoshi
Suzuki, Takahiro
author_facet Daimo, Renya
Ono, Satoshi
Suzuki, Takahiro
contents This paper proposes an adversarial attack method to deep neural networks (DNNs) for monocular depth estimation, i.e., estimating the depth from a single image. Single image depth estimation has improved drastically in recent years due to the development of DNNs. However, vulnerabilities of DNNs for image classification have been revealed by adversarial attacks, and DNNs for monocular depth estimation could contain similar vulnerabilities. Therefore, research on vulnerabilities of DNNs for monocular depth estimation has spread rapidly, but many of them assume white-box conditions where inside information of DNNs is available, or are transferability-based black-box attacks that require a substitute DNN model and a training dataset. Utilizing Evolutionary Multi-objective Optimization, the proposed method in this paper analyzes DNNs under the black-box condition where only output depth maps are available. In addition, the proposed method does not require a substitute DNN that has a similar architecture to the target DNN nor any knowledge about training data used to train the target model. Experimental results showed that the proposed method succeeded in attacking two DNN-based methods that were trained with indoor and outdoor scenes respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2101_10452
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Black-box Adversarial Attacks on Monocular Depth Estimation Using Evolutionary Multi-objective Optimization
Daimo, Renya
Ono, Satoshi
Suzuki, Takahiro
Computer Vision and Pattern Recognition
I.2.10; I.2.m
This paper proposes an adversarial attack method to deep neural networks (DNNs) for monocular depth estimation, i.e., estimating the depth from a single image. Single image depth estimation has improved drastically in recent years due to the development of DNNs. However, vulnerabilities of DNNs for image classification have been revealed by adversarial attacks, and DNNs for monocular depth estimation could contain similar vulnerabilities. Therefore, research on vulnerabilities of DNNs for monocular depth estimation has spread rapidly, but many of them assume white-box conditions where inside information of DNNs is available, or are transferability-based black-box attacks that require a substitute DNN model and a training dataset. Utilizing Evolutionary Multi-objective Optimization, the proposed method in this paper analyzes DNNs under the black-box condition where only output depth maps are available. In addition, the proposed method does not require a substitute DNN that has a similar architecture to the target DNN nor any knowledge about training data used to train the target model. Experimental results showed that the proposed method succeeded in attacking two DNN-based methods that were trained with indoor and outdoor scenes respectively.
title Black-box Adversarial Attacks on Monocular Depth Estimation Using Evolutionary Multi-objective Optimization
topic Computer Vision and Pattern Recognition
I.2.10; I.2.m
url https://arxiv.org/abs/2101.10452