Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313177625> ?p ?o ?g. }
- W4313177625 endingPage "532" @default.
- W4313177625 startingPage "514" @default.
- W4313177625 abstract "Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against learning-based MDE. In particular, we use an optimization-based method to systematically generate stealthy physical-object-oriented adversarial patches to attack depth estimation. We balance the stealth and effectiveness of our attack with object-oriented adversarial design, sensitive region localization, and natural style camouflage. Using real-world driving scenarios, we evaluate our attack on concurrent MDE models and a representative downstream task for AD (i.e., 3D object detection). Experimental results show that our method can generate stealthy, effective, and robust adversarial patches for different target objects and models and achieves more than 6 m mean depth estimation error and 93% attack success rate (ASR) in object detection with a patch of 1/9 of the vehicle’s rear area. Field tests on three different driving routes with a real vehicle indicate that we cause over 6 m mean depth estimation error and reduce the object detection rate from 90.70% to 5.16% in continuous video frames." @default.
- W4313177625 created "2023-01-06" @default.
- W4313177625 creator A5015178659 @default.
- W4313177625 creator A5027961969 @default.
- W4313177625 creator A5044832576 @default.
- W4313177625 creator A5056361355 @default.
- W4313177625 creator A5066645865 @default.
- W4313177625 creator A5084853102 @default.
- W4313177625 creator A5086211361 @default.
- W4313177625 date "2022-01-01" @default.
- W4313177625 modified "2023-10-16" @default.
- W4313177625 title "Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches" @default.
- W4313177625 cites W2000359198 @default.
- W4313177625 cites W2150066425 @default.
- W4313177625 cites W2180612164 @default.
- W4313177625 cites W2475287302 @default.
- W4313177625 cites W2535873859 @default.
- W4313177625 cites W2561138825 @default.
- W4313177625 cites W2604721644 @default.
- W4313177625 cites W2607219512 @default.
- W4313177625 cites W2616028256 @default.
- W4313177625 cites W2618043096 @default.
- W4313177625 cites W2725499676 @default.
- W4313177625 cites W2740323046 @default.
- W4313177625 cites W2934843808 @default.
- W4313177625 cites W2954174912 @default.
- W4313177625 cites W2958109694 @default.
- W4313177625 cites W2963448658 @default.
- W4313177625 cites W2963726920 @default.
- W4313177625 cites W2968296999 @default.
- W4313177625 cites W2969664989 @default.
- W4313177625 cites W2981518351 @default.
- W4313177625 cites W2983371255 @default.
- W4313177625 cites W2985775862 @default.
- W4313177625 cites W2986013765 @default.
- W4313177625 cites W2997811843 @default.
- W4313177625 cites W3034604951 @default.
- W4313177625 cites W3035447895 @default.
- W4313177625 cites W3090358134 @default.
- W4313177625 cites W3097573595 @default.
- W4313177625 cites W3098881644 @default.
- W4313177625 cites W3105806188 @default.
- W4313177625 cites W3107942585 @default.
- W4313177625 cites W3112530000 @default.
- W4313177625 cites W3128390792 @default.
- W4313177625 cites W3156877806 @default.
- W4313177625 cites W3171953850 @default.
- W4313177625 cites W3175682855 @default.
- W4313177625 cites W3176692018 @default.
- W4313177625 cites W3181286780 @default.
- W4313177625 cites W3188394685 @default.
- W4313177625 cites W3193689822 @default.
- W4313177625 cites W3196143276 @default.
- W4313177625 cites W3205856632 @default.
- W4313177625 cites W4245852543 @default.
- W4313177625 doi "https://doi.org/10.1007/978-3-031-19839-7_30" @default.
- W4313177625 hasPublicationYear "2022" @default.
- W4313177625 type Work @default.
- W4313177625 citedByCount "15" @default.
- W4313177625 countsByYear W43131776252022 @default.
- W4313177625 countsByYear W43131776252023 @default.
- W4313177625 crossrefType "book-chapter" @default.
- W4313177625 hasAuthorship W4313177625A5015178659 @default.
- W4313177625 hasAuthorship W4313177625A5027961969 @default.
- W4313177625 hasAuthorship W4313177625A5044832576 @default.
- W4313177625 hasAuthorship W4313177625A5056361355 @default.
- W4313177625 hasAuthorship W4313177625A5066645865 @default.
- W4313177625 hasAuthorship W4313177625A5084853102 @default.
- W4313177625 hasAuthorship W4313177625A5086211361 @default.
- W4313177625 hasBestOaLocation W43131776252 @default.
- W4313177625 hasConcept C108583219 @default.
- W4313177625 hasConcept C153180895 @default.
- W4313177625 hasConcept C154945302 @default.
- W4313177625 hasConcept C2776151529 @default.
- W4313177625 hasConcept C2776196576 @default.
- W4313177625 hasConcept C2781238097 @default.
- W4313177625 hasConcept C31972630 @default.
- W4313177625 hasConcept C37736160 @default.
- W4313177625 hasConcept C41008148 @default.
- W4313177625 hasConcept C65909025 @default.
- W4313177625 hasConceptScore W4313177625C108583219 @default.
- W4313177625 hasConceptScore W4313177625C153180895 @default.
- W4313177625 hasConceptScore W4313177625C154945302 @default.
- W4313177625 hasConceptScore W4313177625C2776151529 @default.
- W4313177625 hasConceptScore W4313177625C2776196576 @default.
- W4313177625 hasConceptScore W4313177625C2781238097 @default.
- W4313177625 hasConceptScore W4313177625C31972630 @default.
- W4313177625 hasConceptScore W4313177625C37736160 @default.
- W4313177625 hasConceptScore W4313177625C41008148 @default.
- W4313177625 hasConceptScore W4313177625C65909025 @default.
- W4313177625 hasLocation W43131776251 @default.
- W4313177625 hasLocation W43131776252 @default.
- W4313177625 hasOpenAccess W4313177625 @default.
- W4313177625 hasPrimaryLocation W43131776251 @default.
- W4313177625 hasRelatedWork W1988485990 @default.
- W4313177625 hasRelatedWork W2007544051 @default.
- W4313177625 hasRelatedWork W2095705906 @default.
- W4313177625 hasRelatedWork W2592945177 @default.