The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems

Vision is a popular and effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, gender, identity, activity and even emotional state of humans within that scene. This raises important questions about t...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-05
Main Authors: Taras, Adam K, Suenderhauf, Niko, Corke, Peter, Dansereau, Donald G
Format: Article
Language:English
Subjects:
Machine vision
Privacy
Robotics
Semantics
System effectiveness
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 Taras, Adam K
Suenderhauf, Niko
Corke, Peter
Dansereau, Donald G
description Vision is a popular and effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, gender, identity, activity and even emotional state of humans within that scene. This raises important questions about the reach, lifespan, and potential misuse of this information. This paper is a call to action to consider privacy in the context of robotic vision. We propose a specific form privacy preservation in which no images are captured or could be reconstructed by an attacker even with full remote access. We present a set of principles by which such systems can be designed, and through a case study in localisation demonstrate in simulation a specific implementation that delivers an important robotic capability in an inherently privacy-preserving manner. This is a first step, and we hope to inspire future works that expand the range of applications open to sighted robotic systems.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2792706683</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2792706683</sourcerecordid><originalsourceid>FETCH-proquest_journals_27927066833</originalsourceid><addsrcrecordid>eNqNyrEKwjAQgOEgCIr6DgfOhZpoW0cRRRcpWFxF9GpTak7vkkrfXgcfwOkfvr-nhtqYWZTNtR6oiUgdx7FOUr1YmKE6FhXCAfEGJTHsXYWMzjcd5Gzby7WLckZBbq27w8mKJQfWQcFB_JvYVx2sgidHDwoCx048PmSs-uWlEZz8OlLT7aZY76In0yug-HNNgd2Xzjpd6jROksyY_64PdpRA4g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2792706683</pqid></control><display><type>article</type><title>The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems</title><source>Publicly Available Content Database</source><creator>Taras, Adam K ; Suenderhauf, Niko ; Corke, Peter ; Dansereau, Donald G</creator><creatorcontrib>Taras, Adam K ; Suenderhauf, Niko ; Corke, Peter ; Dansereau, Donald G</creatorcontrib><description>Vision is a popular and effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, gender, identity, activity and even emotional state of humans within that scene. This raises important questions about the reach, lifespan, and potential misuse of this information. This paper is a call to action to consider privacy in the context of robotic vision. We propose a specific form privacy preservation in which no images are captured or could be reconstructed by an attacker even with full remote access. We present a set of principles by which such systems can be designed, and through a case study in localisation demonstrate in simulation a specific implementation that delivers an important robotic capability in an inherently privacy-preserving manner. This is a first step, and we hope to inspire future works that expand the range of applications open to sighted robotic systems.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Machine vision ; Privacy ; Robotics ; Semantics ; System effectiveness</subject><ispartof>arXiv.org, 2023-05</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by-nc-sa/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/2792706683?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Taras, Adam K</creatorcontrib><creatorcontrib>Suenderhauf, Niko</creatorcontrib><creatorcontrib>Corke, Peter</creatorcontrib><creatorcontrib>Dansereau, Donald G</creatorcontrib><title>The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems</title><title>arXiv.org</title><description>Vision is a popular and effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, gender, identity, activity and even emotional state of humans within that scene. This raises important questions about the reach, lifespan, and potential misuse of this information. This paper is a call to action to consider privacy in the context of robotic vision. We propose a specific form privacy preservation in which no images are captured or could be reconstructed by an attacker even with full remote access. We present a set of principles by which such systems can be designed, and through a case study in localisation demonstrate in simulation a specific implementation that delivers an important robotic capability in an inherently privacy-preserving manner. This is a first step, and we hope to inspire future works that expand the range of applications open to sighted robotic systems.</description><subject>Machine vision</subject><subject>Privacy</subject><subject>Robotics</subject><subject>Semantics</subject><subject>System effectiveness</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNyrEKwjAQgOEgCIr6DgfOhZpoW0cRRRcpWFxF9GpTak7vkkrfXgcfwOkfvr-nhtqYWZTNtR6oiUgdx7FOUr1YmKE6FhXCAfEGJTHsXYWMzjcd5Gzby7WLckZBbq27w8mKJQfWQcFB_JvYVx2sgidHDwoCx048PmSs-uWlEZz8OlLT7aZY76In0yug-HNNgd2Xzjpd6jROksyY_64PdpRA4g</recordid><startdate>20230510</startdate><enddate>20230510</enddate><creator>Taras, Adam K</creator><creator>Suenderhauf, Niko</creator><creator>Corke, Peter</creator><creator>Dansereau, Donald G</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>20230510</creationdate><title>The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems</title><author>Taras, Adam K ; Suenderhauf, Niko ; Corke, Peter ; Dansereau, Donald G</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27927066833</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Machine vision</topic><topic>Privacy</topic><topic>Robotics</topic><topic>Semantics</topic><topic>System effectiveness</topic><toplevel>online_resources</toplevel><creatorcontrib>Taras, Adam K</creatorcontrib><creatorcontrib>Suenderhauf, Niko</creatorcontrib><creatorcontrib>Corke, Peter</creatorcontrib><creatorcontrib>Dansereau, Donald G</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>ProQuest Databases</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Taras, Adam K</au><au>Suenderhauf, Niko</au><au>Corke, Peter</au><au>Dansereau, Donald G</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems</atitle><jtitle>arXiv.org</jtitle><date>2023-05-10</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Vision is a popular and effective sensor for robotics from which we can derive rich information about the environment: the geometry and semantics of the scene, as well as the age, gender, identity, activity and even emotional state of humans within that scene. This raises important questions about the reach, lifespan, and potential misuse of this information. This paper is a call to action to consider privacy in the context of robotic vision. We propose a specific form privacy preservation in which no images are captured or could be reconstructed by an attacker even with full remote access. We present a set of principles by which such systems can be designed, and through a case study in localisation demonstrate in simulation a specific implementation that delivers an important robotic capability in an inherently privacy-preserving manner. This is a first step, and we hope to inspire future works that expand the range of applications open to sighted robotic systems.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2792706683
source Publicly Available Content Database
subjects Machine vision
Privacy
Robotics
Semantics
System effectiveness
title The Need for Inherently Privacy-Preserving Vision in Trustworthy Autonomous Systems
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T21%3A17%3A33IST&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:book&rft.genre=document&rft.atitle=The%20Need%20for%20Inherently%20Privacy-Preserving%20Vision%20in%20Trustworthy%20Autonomous%20Systems&rft.jtitle=arXiv.org&rft.au=Taras,%20Adam%20K&rft.date=2023-05-10&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2792706683%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_27927066833%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2792706683&rft_id=info:pmid/&rfr_iscdi=true