FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201437289> ?p ?o ?g. }

• W3201437289 endingPage "36" @default.
• W3201437289 startingPage "27" @default.
• W3201437289 abstract "Deep learning models have been demonstrated vulnerable to adversarial attacks even with imperceptible perturbations. As such, the reliability of existing deep neural networks-based autonomous driving systems can suffer. However, deep 3D models have applications in various Cyber-Physical Systems (CPSs) with safety-critical requirements, particularly autonomous driving systems. In this paper, the robustness of deep 3D object detection models under adversarial point cloud perturbations has been investigated. A novel method is developed to generate 3D adversarial examples from point cloud perturbations, which are common due to the intrinsic characteristics of the data captured by 3D sensors, e.g., LiDAR. The generation of adversarial samples is supervised by a dual loss, which constitutes an adversarial loss and a perturbation loss. The adversarial loss produces a point cloud with the property of aggressiveness, while the perturbation loss enforces the produced point cloud subject to visual imperception. We demonstrate that the method can successfully attack 3D object detection models in most cases, and expose their vulnerability to physical-world attacks in the form of point cloud perturbations. We perform a thorough evaluation of popular deep 3D object detectors in an adversarial setting on the KITTI vision benchmark. Experimental results show that current deep 3D object detection models are susceptible to adversarial attacks in the context of autonomous driving, and their performances are degraded by a large margin in the presence of adversarial point clouds generated by the proposed method." @default.
• W3201437289 created "2021-09-27" @default.
• W3201437289 creator A5002219416 @default.
• W3201437289 creator A5018927991 @default.
• W3201437289 creator A5075116817 @default.
• W3201437289 creator A5076726522 @default.
• W3201437289 creator A5083891468 @default.
• W3201437289 date "2021-11-01" @default.
• W3201437289 modified "2023-10-01" @default.
• W3201437289 title "Adversarial point cloud perturbations against 3D object detection in autonomous driving systems" @default.
• W3201437289 cites W2007200979 @default.
• W3201437289 cites W2150066425 @default.
• W3201437289 cites W2180612164 @default.
• W3201437289 cites W2619344387 @default.
• W3201437289 cites W2798965597 @default.
• W3201437289 cites W2894703649 @default.
• W3201437289 cites W2949708697 @default.
• W3201437289 cites W2958109694 @default.
• W3201437289 cites W2962700793 @default.
• W3201437289 cites W2962818872 @default.
• W3201437289 cites W2963068442 @default.
• W3201437289 cites W2963662610 @default.
• W3201437289 cites W2963727135 @default.
• W3201437289 cites W2964097310 @default.
• W3201437289 cites W2971089407 @default.
• W3201437289 cites W2981199548 @default.
• W3201437289 cites W2981979099 @default.
• W3201437289 cites W2982104318 @default.
• W3201437289 cites W2990258745 @default.
• W3201437289 cites W2997811843 @default.
• W3201437289 cites W3005560595 @default.
• W3201437289 cites W3034314779 @default.
• W3201437289 cites W3034376720 @default.
• W3201437289 cites W3034455297 @default.
• W3201437289 cites W3034602892 @default.
• W3201437289 cites W3034707001 @default.
• W3201437289 cites W3035394681 @default.
• W3201437289 cites W3035584216 @default.
• W3201437289 cites W3039448353 @default.
• W3201437289 cites W3043669398 @default.
• W3201437289 cites W3049386060 @default.
• W3201437289 cites W3097455612 @default.
• W3201437289 cites W3098881644 @default.
• W3201437289 doi "https://doi.org/10.1016/j.neucom.2021.09.027" @default.
• W3201437289 hasPublicationYear "2021" @default.
• W3201437289 type Work @default.
• W3201437289 sameAs 3201437289 @default.
• W3201437289 citedByCount "14" @default.
• W3201437289 countsByYear W32014372892022 @default.
• W3201437289 countsByYear W32014372892023 @default.
• W3201437289 crossrefType "journal-article" @default.
• W3201437289 hasAuthorship W3201437289A5002219416 @default.
• W3201437289 hasAuthorship W3201437289A5018927991 @default.
• W3201437289 hasAuthorship W3201437289A5075116817 @default.
• W3201437289 hasAuthorship W3201437289A5076726522 @default.
• W3201437289 hasAuthorship W3201437289A5083891468 @default.
• W3201437289 hasConcept C104317684 @default.
• W3201437289 hasConcept C108583219 @default.
• W3201437289 hasConcept C127313418 @default.
• W3201437289 hasConcept C131979681 @default.
• W3201437289 hasConcept C153180895 @default.
• W3201437289 hasConcept C154945302 @default.
• W3201437289 hasConcept C185592680 @default.
• W3201437289 hasConcept C2776151529 @default.
• W3201437289 hasConcept C31972630 @default.
• W3201437289 hasConcept C37736160 @default.
• W3201437289 hasConcept C41008148 @default.
• W3201437289 hasConcept C51399673 @default.
• W3201437289 hasConcept C55493867 @default.
• W3201437289 hasConcept C62649853 @default.
• W3201437289 hasConcept C63479239 @default.
• W3201437289 hasConcept C79403827 @default.
• W3201437289 hasConceptScore W3201437289C104317684 @default.
• W3201437289 hasConceptScore W3201437289C108583219 @default.
• W3201437289 hasConceptScore W3201437289C127313418 @default.
• W3201437289 hasConceptScore W3201437289C131979681 @default.
• W3201437289 hasConceptScore W3201437289C153180895 @default.
• W3201437289 hasConceptScore W3201437289C154945302 @default.
• W3201437289 hasConceptScore W3201437289C185592680 @default.
• W3201437289 hasConceptScore W3201437289C2776151529 @default.
• W3201437289 hasConceptScore W3201437289C31972630 @default.
• W3201437289 hasConceptScore W3201437289C37736160 @default.
• W3201437289 hasConceptScore W3201437289C41008148 @default.
• W3201437289 hasConceptScore W3201437289C51399673 @default.
• W3201437289 hasConceptScore W3201437289C55493867 @default.
• W3201437289 hasConceptScore W3201437289C62649853 @default.
• W3201437289 hasConceptScore W3201437289C63479239 @default.
• W3201437289 hasConceptScore W3201437289C79403827 @default.
• W3201437289 hasFunder F4320325964 @default.
• W3201437289 hasLocation W32014372891 @default.
• W3201437289 hasOpenAccess W3201437289 @default.
• W3201437289 hasPrimaryLocation W32014372891 @default.
• W3201437289 hasRelatedWork W2035976912 @default.
• W3201437289 hasRelatedWork W2541791370 @default.
• W3201437289 hasRelatedWork W3081118561 @default.
• W3201437289 hasRelatedWork W3094187672 @default.
• W3201437289 hasRelatedWork W3157544141 @default.
• W3201437289 hasRelatedWork W3193857078 @default.

• next