Object Removal Attacks on LiDAR-based 3D Object Detectors
LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, eve...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2021-02 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Hau, Zhongyuan Co, Kenneth T Demetriou, Soteris Lupu, Emil C |
| description | LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, even more dangerous class of attacks, namely Object Removal Attacks (ORAs). ORAs aim to force 3D object detectors to fail. We leverage the default setting of LiDARs that record a single return signal per direction to perturb point clouds in the region of interest (RoI) of 3D objects. By injecting illegitimate points behind the target object, we effectively shift points away from the target objects' RoIs. Our initial results using a simple random point selection strategy show that the attack is effective in degrading the performance of commonly used 3D object detection models. |
| doi_str_mv | 10.48550/arxiv.2102.03722 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2102_03722</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2487645361</sourcerecordid><originalsourceid>FETCH-LOGICAL-a952-405fefc08067099637373ec00a4f271e1085ddc1a046c3c00281561845ebfc7a3</originalsourceid><addsrcrecordid>eNotj01Lw0AURQdBsNT-AFcOuE588-Yzy9CoFQKF0n2YTCaQ2DZ1Ji36741teYsLj8PlHkKeGKTCSAmvNvx05xQZYApcI96RGXLOEiMQH8gixh4AUGmUks9Itq5770a68fvhbHc0H0frviIdDrTsinyT1Db6hvKC3sDCj1MMIT6S-9buol_cck6272_b5Sop1x-fy7xMbCYxESBb3zowoDRkmeJ6Ou8ArGhRM8_AyKZxzIJQjk9_NEwqZoT0deu05XPyfK29eFXH0O1t-K3-_aqL30S8XIljGL5PPo5VP5zCYdpUoTBaCckV43-NZk-l</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2487645361</pqid></control><display><type>article</type><title>Object Removal Attacks on LiDAR-based 3D Object Detectors</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Hau, Zhongyuan ; Co, Kenneth T ; Demetriou, Soteris ; Lupu, Emil C</creator><creatorcontrib>Hau, Zhongyuan ; Co, Kenneth T ; Demetriou, Soteris ; Lupu, Emil C</creatorcontrib><description>LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, even more dangerous class of attacks, namely Object Removal Attacks (ORAs). ORAs aim to force 3D object detectors to fail. We leverage the default setting of LiDARs that record a single return signal per direction to perturb point clouds in the region of interest (RoI) of 3D objects. By injecting illegitimate points behind the target object, we effectively shift points away from the target objects' RoIs. Our initial results using a simple random point selection strategy show that the attack is effective in degrading the performance of commonly used 3D object detection models.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2102.03722</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Cryptography and Security ; Computer Science - Learning ; Detectors ; Lidar ; Object recognition ; Performance degradation ; Three dimensional models</subject><ispartof>arXiv.org, 2021-02</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,781,882,27906</link.rule.ids><backlink>$$Uhttps://doi.org/10.14722/autosec.2021.23$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2102.03722$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hau, Zhongyuan</creatorcontrib><creatorcontrib>Co, Kenneth T</creatorcontrib><creatorcontrib>Demetriou, Soteris</creatorcontrib><creatorcontrib>Lupu, Emil C</creatorcontrib><title>Object Removal Attacks on LiDAR-based 3D Object Detectors</title><title>arXiv.org</title><description>LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, even more dangerous class of attacks, namely Object Removal Attacks (ORAs). ORAs aim to force 3D object detectors to fail. We leverage the default setting of LiDARs that record a single return signal per direction to perturb point clouds in the region of interest (RoI) of 3D objects. By injecting illegitimate points behind the target object, we effectively shift points away from the target objects' RoIs. Our initial results using a simple random point selection strategy show that the attack is effective in degrading the performance of commonly used 3D object detection models.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Cryptography and Security</subject><subject>Computer Science - Learning</subject><subject>Detectors</subject><subject>Lidar</subject><subject>Object recognition</subject><subject>Performance degradation</subject><subject>Three dimensional models</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj01Lw0AURQdBsNT-AFcOuE588-Yzy9CoFQKF0n2YTCaQ2DZ1Ji36741teYsLj8PlHkKeGKTCSAmvNvx05xQZYApcI96RGXLOEiMQH8gixh4AUGmUks9Itq5770a68fvhbHc0H0frviIdDrTsinyT1Db6hvKC3sDCj1MMIT6S-9buol_cck6272_b5Sop1x-fy7xMbCYxESBb3zowoDRkmeJ6Ou8ArGhRM8_AyKZxzIJQjk9_NEwqZoT0deu05XPyfK29eFXH0O1t-K3-_aqL30S8XIljGL5PPo5VP5zCYdpUoTBaCckV43-NZk-l</recordid><startdate>20210207</startdate><enddate>20210207</enddate><creator>Hau, Zhongyuan</creator><creator>Co, Kenneth T</creator><creator>Demetriou, Soteris</creator><creator>Lupu, Emil C</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><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210207</creationdate><title>Object Removal Attacks on LiDAR-based 3D Object Detectors</title><author>Hau, Zhongyuan ; Co, Kenneth T ; Demetriou, Soteris ; Lupu, Emil C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a952-405fefc08067099637373ec00a4f271e1085ddc1a046c3c00281561845ebfc7a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Cryptography and Security</topic><topic>Computer Science - Learning</topic><topic>Detectors</topic><topic>Lidar</topic><topic>Object recognition</topic><topic>Performance degradation</topic><topic>Three dimensional models</topic><toplevel>online_resources</toplevel><creatorcontrib>Hau, Zhongyuan</creatorcontrib><creatorcontrib>Co, Kenneth T</creatorcontrib><creatorcontrib>Demetriou, Soteris</creatorcontrib><creatorcontrib>Lupu, Emil C</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</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><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hau, Zhongyuan</au><au>Co, Kenneth T</au><au>Demetriou, Soteris</au><au>Lupu, Emil C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Object Removal Attacks on LiDAR-based 3D Object Detectors</atitle><jtitle>arXiv.org</jtitle><date>2021-02-07</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, even more dangerous class of attacks, namely Object Removal Attacks (ORAs). ORAs aim to force 3D object detectors to fail. We leverage the default setting of LiDARs that record a single return signal per direction to perturb point clouds in the region of interest (RoI) of 3D objects. By injecting illegitimate points behind the target object, we effectively shift points away from the target objects' RoIs. Our initial results using a simple random point selection strategy show that the attack is effective in degrading the performance of commonly used 3D object detection models.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2102.03722</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2021-02 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2102_03722 |
| source | arXiv.org; Free E- Journals |
| subjects | Computer Science - Computer Vision and Pattern Recognition Computer Science - Cryptography and Security Computer Science - Learning Detectors Lidar Object recognition Performance degradation Three dimensional models |
| title | Object Removal Attacks on LiDAR-based 3D Object Detectors |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T06%3A38%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Object%20Removal%20Attacks%20on%20LiDAR-based%203D%20Object%20Detectors&rft.jtitle=arXiv.org&rft.au=Hau,%20Zhongyuan&rft.date=2021-02-07&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2102.03722&rft_dat=%3Cproquest_arxiv%3E2487645361%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2487645361&rft_id=info:pmid/&rfr_iscdi=true |