Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380883423> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4380883423 endingPage "103345" @default.
- W4380883423 startingPage "103345" @default.
- W4380883423 abstract "With the development of machine learning models throughout industries, there has been a corresponding increase in research demonstrating its vulnerability to adversarial examples (AE). Realizing physically robust AE that survive real-world environmental conditions faces the challenges such as varied viewing distances or angles. Laser beam-based methods claim to overcome the obviousness, semi-permanence, and unchangeable drawbacks of adversarial patches. However, laser beam-based AE could not be captured by the camera under daylight, which makes the application scenarios limited. In this research, we introduce Adversarial Spot Light (AdvSL), a novel approach that enables adversaries to build physically robust real-world AE by utilizing spotlight flashlights. Since the spotlight flashlights may be switched on and off as required, AdvSL allows adversaries to perform more flexible attacks than adversarial patches. Especially, AdvSL is feasible in a variety of ambient light conditions. As a first step, we modeled a spot light with a set of parameters that can be physically controlled by the adversary. To determine the optimal parameters for the light, a heuristic optimization approach is adopted. Further, we use the k-random-restart technique to prevent the approach from being stuck in a local optimum. To demonstrate the effectiveness of the proposed approach, we conduct experiments under different physical conditions, including indoor and outdoor tests. In the digital test, AdvSL causes misclassifications on state-of-the-art neural networks with up to 93.7% attack success rate. In the outdoor test, AdvSL causes misclassifications on the traffic sign classification model with up to 84% attack success rate. In the physical setting, experiments show that the AdvSL is robust in non-bright settings and is feasible in bright settings. Finally, we discuss the defense of AdvSL and evaluate an adaptive defender using adversarial learning, which is able to reduce the attack success rate from 92.2% to 54.8% in the digital." @default.
- W4380883423 created "2023-06-17" @default.
- W4380883423 creator A5019060976 @default.
- W4380883423 creator A5052431621 @default.
- W4380883423 creator A5067210224 @default.
- W4380883423 creator A5069206151 @default.
- W4380883423 creator A5074292957 @default.
- W4380883423 date "2023-09-01" @default.
- W4380883423 modified "2023-09-27" @default.
- W4380883423 title "Light can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Spot Light" @default.
- W4380883423 cites W2024060531 @default.
- W4380883423 cites W2126628495 @default.
- W4380883423 cites W2143560894 @default.
- W4380883423 cites W2618530766 @default.
- W4380883423 cites W2973021304 @default.
- W4380883423 cites W3103557498 @default.
- W4380883423 doi "https://doi.org/10.1016/j.cose.2023.103345" @default.
- W4380883423 hasPublicationYear "2023" @default.
- W4380883423 type Work @default.
- W4380883423 citedByCount "0" @default.
- W4380883423 crossrefType "journal-article" @default.
- W4380883423 hasAuthorship W4380883423A5019060976 @default.
- W4380883423 hasAuthorship W4380883423A5052431621 @default.
- W4380883423 hasAuthorship W4380883423A5067210224 @default.
- W4380883423 hasAuthorship W4380883423A5069206151 @default.
- W4380883423 hasAuthorship W4380883423A5074292957 @default.
- W4380883423 hasConcept C120665830 @default.
- W4380883423 hasConcept C121332964 @default.
- W4380883423 hasConcept C149277555 @default.
- W4380883423 hasConcept C154945302 @default.
- W4380883423 hasConcept C173801870 @default.
- W4380883423 hasConcept C177264268 @default.
- W4380883423 hasConcept C199360897 @default.
- W4380883423 hasConcept C37736160 @default.
- W4380883423 hasConcept C38652104 @default.
- W4380883423 hasConcept C41008148 @default.
- W4380883423 hasConcept C41065033 @default.
- W4380883423 hasConcept C95713431 @default.
- W4380883423 hasConceptScore W4380883423C120665830 @default.
- W4380883423 hasConceptScore W4380883423C121332964 @default.
- W4380883423 hasConceptScore W4380883423C149277555 @default.
- W4380883423 hasConceptScore W4380883423C154945302 @default.
- W4380883423 hasConceptScore W4380883423C173801870 @default.
- W4380883423 hasConceptScore W4380883423C177264268 @default.
- W4380883423 hasConceptScore W4380883423C199360897 @default.
- W4380883423 hasConceptScore W4380883423C37736160 @default.
- W4380883423 hasConceptScore W4380883423C38652104 @default.
- W4380883423 hasConceptScore W4380883423C41008148 @default.
- W4380883423 hasConceptScore W4380883423C41065033 @default.
- W4380883423 hasConceptScore W4380883423C95713431 @default.
- W4380883423 hasLocation W43808834231 @default.
- W4380883423 hasOpenAccess W4380883423 @default.
- W4380883423 hasPrimaryLocation W43808834231 @default.
- W4380883423 hasRelatedWork W141916771 @default.
- W4380883423 hasRelatedWork W2079101048 @default.
- W4380883423 hasRelatedWork W2089917086 @default.
- W4380883423 hasRelatedWork W2522301850 @default.
- W4380883423 hasRelatedWork W286553814 @default.
- W4380883423 hasRelatedWork W3034953030 @default.
- W4380883423 hasRelatedWork W4248052496 @default.
- W4380883423 hasRelatedWork W4251088474 @default.
- W4380883423 hasRelatedWork W43121067 @default.
- W4380883423 hasRelatedWork W4362599004 @default.
- W4380883423 hasVolume "132" @default.
- W4380883423 isParatext "false" @default.
- W4380883423 isRetracted "false" @default.
- W4380883423 workType "article" @default.