Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313305544> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4313305544 abstract "The deep neural network (DNN) models for object detection using camera images are widely adopted in autonomous vehicles. However, DNN models are shown to be susceptible to adversarial image perturbations. In the existing methods of generating the adversarial image perturbations, optimizations take each incoming image frame as the decision variable to generate an image perturbation. Therefore, given a new image, the typically computationally-expensive optimization needs to start over as there is no learning between the independent optimizations. Very few approaches have been developed for attacking online image streams while considering the underlying physical dynamics of autonomous vehicles, their mission, and the environment. We propose a multi-level stochastic optimization framework that monitors an attacker's capability of generating the adversarial perturbations. Based on this capability level, a binary decision attack/not attack is introduced to enhance the effectiveness of the attacker. We evaluate our proposed multi-level image attack framework using simulations for vision-guided autonomous vehicles and actual tests with a small indoor drone in an office environment. The results show our method's capability to generate the image attack in real-time while monitoring when the attacker is proficient given state estimates." @default.
- W4313305544 created "2023-01-06" @default.
- W4313305544 creator A5047245404 @default.
- W4313305544 creator A5080473137 @default.
- W4313305544 creator A5089726422 @default.
- W4313305544 date "2022-12-27" @default.
- W4313305544 modified "2023-09-29" @default.
- W4313305544 title "Learning When to Use Adaptive Adversarial Image Perturbations against Autonomous Vehicles" @default.
- W4313305544 doi "https://doi.org/10.48550/arxiv.2212.13667" @default.
- W4313305544 hasPublicationYear "2022" @default.
- W4313305544 type Work @default.
- W4313305544 citedByCount "0" @default.
- W4313305544 crossrefType "posted-content" @default.
- W4313305544 hasAuthorship W4313305544A5047245404 @default.
- W4313305544 hasAuthorship W4313305544A5080473137 @default.
- W4313305544 hasAuthorship W4313305544A5089726422 @default.
- W4313305544 hasBestOaLocation W43133055441 @default.
- W4313305544 hasConcept C108583219 @default.
- W4313305544 hasConcept C115961682 @default.
- W4313305544 hasConcept C119857082 @default.
- W4313305544 hasConcept C153180895 @default.
- W4313305544 hasConcept C154945302 @default.
- W4313305544 hasConcept C2776151529 @default.
- W4313305544 hasConcept C2984842247 @default.
- W4313305544 hasConcept C31972630 @default.
- W4313305544 hasConcept C37736160 @default.
- W4313305544 hasConcept C41008148 @default.
- W4313305544 hasConcept C54355233 @default.
- W4313305544 hasConcept C59519942 @default.
- W4313305544 hasConcept C79403827 @default.
- W4313305544 hasConcept C86803240 @default.
- W4313305544 hasConceptScore W4313305544C108583219 @default.
- W4313305544 hasConceptScore W4313305544C115961682 @default.
- W4313305544 hasConceptScore W4313305544C119857082 @default.
- W4313305544 hasConceptScore W4313305544C153180895 @default.
- W4313305544 hasConceptScore W4313305544C154945302 @default.
- W4313305544 hasConceptScore W4313305544C2776151529 @default.
- W4313305544 hasConceptScore W4313305544C2984842247 @default.
- W4313305544 hasConceptScore W4313305544C31972630 @default.
- W4313305544 hasConceptScore W4313305544C37736160 @default.
- W4313305544 hasConceptScore W4313305544C41008148 @default.
- W4313305544 hasConceptScore W4313305544C54355233 @default.
- W4313305544 hasConceptScore W4313305544C59519942 @default.
- W4313305544 hasConceptScore W4313305544C79403827 @default.
- W4313305544 hasConceptScore W4313305544C86803240 @default.
- W4313305544 hasLocation W43133055441 @default.
- W4313305544 hasOpenAccess W4313305544 @default.
- W4313305544 hasPrimaryLocation W43133055441 @default.
- W4313305544 hasRelatedWork W2180612164 @default.
- W4313305544 hasRelatedWork W2610321374 @default.
- W4313305544 hasRelatedWork W2952919291 @default.
- W4313305544 hasRelatedWork W2970686063 @default.
- W4313305544 hasRelatedWork W3193857078 @default.
- W4313305544 hasRelatedWork W4224881325 @default.
- W4313305544 hasRelatedWork W4226383822 @default.
- W4313305544 hasRelatedWork W4293054861 @default.
- W4313305544 hasRelatedWork W4298388782 @default.
- W4313305544 hasRelatedWork W4300837091 @default.
- W4313305544 isParatext "false" @default.
- W4313305544 isRetracted "false" @default.
- W4313305544 workType "article" @default.