Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models

A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a LIDAR sensor as inputs. In this work, we perform the first stud...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-09
Main Authors: Park, Won, Liu, Nan, Chen, Qi Alfred, Z Morley Mao
Format: Article
Language:English
Subjects:
Lidar
Object recognition
Robustness
Sensors
Spoofing
Three dimensional models
Two dimensional models
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Park, Won
Liu, Nan
Chen, Qi Alfred
Z Morley Mao
description A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a LIDAR sensor as inputs. In this work, we perform the first study to analyze the robustness of a high-performance, open source sensor fusion model architecture towards adversarial attacks and challenge the popular belief that the use of additional sensors automatically mitigate the risk of adversarial attacks. We find that despite the use of a LIDAR sensor, the model is vulnerable to our purposefully crafted image-based adversarial attacks including disappearance, universal patch, and spoofing. After identifying the underlying reason, we explore some potential defenses and provide some recommendations for improved sensor fusion models.
doi_str_mv 10.48550/arxiv.2109.06363
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2573160653</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2573160653</sourcerecordid><originalsourceid>FETCH-LOGICAL-a523-f5a99f87fd52dbfc379d31a75991182a3926012344f96839c82e3daa25d6ade53</originalsourceid><addsrcrecordid>eNotjsFKAzEUAIMgWGo_wFvA89bkvU124620VoVKQXvzUF6bRLYsG83bLerXq9jTMJdhhLjSalrWxqgbyp_NcQpauamyaPFMjABRF3UJcCEmzAelFNgKjMGReH0JHacsZ_4YMlNuqJWbTE3Pt3LWUfv13XRv8jntBu67wCxTlLiQ690h7Hu5CP0vmtTJU2Y58J89JR9avhTnkVoOkxPHYrO828wfitX6_nE-WxVkAItoyLlYV9Eb8Lu4x8p51FQZ57SugdCBVRqwLKOzNbp9DQE9ERhvyQeDY3H9n33P6WMI3G8Paci_77wFU6G2yhrEH9ToU9s</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2573160653</pqid></control><display><type>article</type><title>Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Park, Won ; Liu, Nan ; Chen, Qi Alfred ; Z Morley Mao</creator><creatorcontrib>Park, Won ; Liu, Nan ; Chen, Qi Alfred ; Z Morley Mao</creatorcontrib><description>A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a LIDAR sensor as inputs. In this work, we perform the first study to analyze the robustness of a high-performance, open source sensor fusion model architecture towards adversarial attacks and challenge the popular belief that the use of additional sensors automatically mitigate the risk of adversarial attacks. We find that despite the use of a LIDAR sensor, the model is vulnerable to our purposefully crafted image-based adversarial attacks including disappearance, universal patch, and spoofing. After identifying the underlying reason, we explore some potential defenses and provide some recommendations for improved sensor fusion models.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2109.06363</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Lidar ; Object recognition ; Robustness ; Sensors ; Spoofing ; Three dimensional models ; Two dimensional models</subject><ispartof>arXiv.org, 2021-09</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2573160653?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,27925,37012,44590</link.rule.ids></links><search><creatorcontrib>Park, Won</creatorcontrib><creatorcontrib>Liu, Nan</creatorcontrib><creatorcontrib>Chen, Qi Alfred</creatorcontrib><creatorcontrib>Z Morley Mao</creatorcontrib><title>Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models</title><title>arXiv.org</title><description>A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a LIDAR sensor as inputs. In this work, we perform the first study to analyze the robustness of a high-performance, open source sensor fusion model architecture towards adversarial attacks and challenge the popular belief that the use of additional sensors automatically mitigate the risk of adversarial attacks. We find that despite the use of a LIDAR sensor, the model is vulnerable to our purposefully crafted image-based adversarial attacks including disappearance, universal patch, and spoofing. After identifying the underlying reason, we explore some potential defenses and provide some recommendations for improved sensor fusion models.</description><subject>Lidar</subject><subject>Object recognition</subject><subject>Robustness</subject><subject>Sensors</subject><subject>Spoofing</subject><subject>Three dimensional models</subject><subject>Two dimensional models</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNotjsFKAzEUAIMgWGo_wFvA89bkvU124620VoVKQXvzUF6bRLYsG83bLerXq9jTMJdhhLjSalrWxqgbyp_NcQpauamyaPFMjABRF3UJcCEmzAelFNgKjMGReH0JHacsZ_4YMlNuqJWbTE3Pt3LWUfv13XRv8jntBu67wCxTlLiQ690h7Hu5CP0vmtTJU2Y58J89JR9avhTnkVoOkxPHYrO828wfitX6_nE-WxVkAItoyLlYV9Eb8Lu4x8p51FQZ57SugdCBVRqwLKOzNbp9DQE9ERhvyQeDY3H9n33P6WMI3G8Paci_77wFU6G2yhrEH9ToU9s</recordid><startdate>20210913</startdate><enddate>20210913</enddate><creator>Park, Won</creator><creator>Liu, Nan</creator><creator>Chen, Qi Alfred</creator><creator>Z Morley Mao</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210913</creationdate><title>Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models</title><author>Park, Won ; Liu, Nan ; Chen, Qi Alfred ; Z Morley Mao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a523-f5a99f87fd52dbfc379d31a75991182a3926012344f96839c82e3daa25d6ade53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Lidar</topic><topic>Object recognition</topic><topic>Robustness</topic><topic>Sensors</topic><topic>Spoofing</topic><topic>Three dimensional models</topic><topic>Two dimensional models</topic><toplevel>online_resources</toplevel><creatorcontrib>Park, Won</creatorcontrib><creatorcontrib>Liu, Nan</creatorcontrib><creatorcontrib>Chen, Qi Alfred</creatorcontrib><creatorcontrib>Z Morley Mao</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest Engineering Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Park, Won</au><au>Liu, Nan</au><au>Chen, Qi Alfred</au><au>Z Morley Mao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models</atitle><jtitle>arXiv.org</jtitle><date>2021-09-13</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a LIDAR sensor as inputs. In this work, we perform the first study to analyze the robustness of a high-performance, open source sensor fusion model architecture towards adversarial attacks and challenge the popular belief that the use of additional sensors automatically mitigate the risk of adversarial attacks. We find that despite the use of a LIDAR sensor, the model is vulnerable to our purposefully crafted image-based adversarial attacks including disappearance, universal patch, and spoofing. After identifying the underlying reason, we explore some potential defenses and provide some recommendations for improved sensor fusion models.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2109.06363</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2573160653
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Lidar
Object recognition
Robustness
Sensors
Spoofing
Three dimensional models
Two dimensional models
title Sensor Adversarial Traits: Analyzing Robustness of 3D Object Detection Sensor Fusion Models
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T11%3A17%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Sensor%20Adversarial%20Traits:%20Analyzing%20Robustness%20of%203D%20Object%20Detection%20Sensor%20Fusion%20Models&rft.jtitle=arXiv.org&rft.au=Park,%20Won&rft.date=2021-09-13&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2109.06363&rft_dat=%3Cproquest%3E2573160653%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a523-f5a99f87fd52dbfc379d31a75991182a3926012344f96839c82e3daa25d6ade53%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2573160653&rft_id=info:pmid/&rfr_iscdi=true