Matches in SemOpenAlex for { <https://semopenalex.org/work/W4364305298> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4364305298 abstract "Autonomous vehicles rely on computer vision models for perception, which have been shown to be vulnerable to adversarial attacks. These attacks pose various risks from reducing user confidence in the technology to directly influencing the technology to make a particular action [1]. Research in adversarial machine learning (ML) has led to increased awareness of ML’s vulnerabilities to such attacks and strategies to mitigate their effects and enhance ML generalizability [1]. Although there exists a dataset for assessing a computer vision model’s efficacy against adversarial attacks in the real-world [2], there is no such dataset for benchmarking computer vision algorithms for autonomous vehicles. This effort is a preliminary study on publicly available datasets for self-driving applications through the lens of adversarial ML. We include a discussion of attacks that have been performed in this space. From black-box to white-box attacks, the more knowledge is available to the adversary, the more they can leverage to employ the attack [1]. Adversaries are fully capable of utilizing the publicly available datasets to test their own black-box attacks [3], [4]. Adversarial examples can be useful in both enhancing algorithm resilience to these attacks through inclusion in training [5] as well as for use in benchmarking current approaches against the attacks [2]. Building resilient autonomy in transportation will require mitigation of any vulnerabilities, especially those from potential adversaries. This survey of datasets and attacks on self-driving vehicles is a first step in developing a dataset of adversarial attacks in this domain. The dataset can assist current and future computer vision research in self-driving to benchmark algorithm effectiveness against such attacks in the real-world." @default.
- W4364305298 created "2023-04-12" @default.
- W4364305298 creator A5005283589 @default.
- W4364305298 creator A5006645244 @default.
- W4364305298 date "2022-10-11" @default.
- W4364305298 modified "2023-10-18" @default.
- W4364305298 title "Adversarial Examples in Self-Driving: A Review of Available Datasets and Attacks" @default.
- W4364305298 cites W2150066425 @default.
- W4364305298 cites W2558027072 @default.
- W4364305298 cites W2884877436 @default.
- W4364305298 cites W2919491917 @default.
- W4364305298 cites W3000280594 @default.
- W4364305298 cites W3025279871 @default.
- W4364305298 cites W3043046767 @default.
- W4364305298 cites W3047375952 @default.
- W4364305298 cites W3090843930 @default.
- W4364305298 cites W3098881644 @default.
- W4364305298 cites W3209102426 @default.
- W4364305298 cites W4205382418 @default.
- W4364305298 cites W4225463226 @default.
- W4364305298 cites W4308217449 @default.
- W4364305298 cites W4312741812 @default.
- W4364305298 cites W4312840203 @default.
- W4364305298 doi "https://doi.org/10.1109/aipr57179.2022.10092221" @default.
- W4364305298 hasPublicationYear "2022" @default.
- W4364305298 type Work @default.
- W4364305298 citedByCount "0" @default.
- W4364305298 crossrefType "proceedings-article" @default.
- W4364305298 hasAuthorship W4364305298A5005283589 @default.
- W4364305298 hasAuthorship W4364305298A5006645244 @default.
- W4364305298 hasConcept C105795698 @default.
- W4364305298 hasConcept C119857082 @default.
- W4364305298 hasConcept C127413603 @default.
- W4364305298 hasConcept C144133560 @default.
- W4364305298 hasConcept C153083717 @default.
- W4364305298 hasConcept C154945302 @default.
- W4364305298 hasConcept C162853370 @default.
- W4364305298 hasConcept C22212356 @default.
- W4364305298 hasConcept C27158222 @default.
- W4364305298 hasConcept C2778403875 @default.
- W4364305298 hasConcept C3018391801 @default.
- W4364305298 hasConcept C33923547 @default.
- W4364305298 hasConcept C37736160 @default.
- W4364305298 hasConcept C38652104 @default.
- W4364305298 hasConcept C41008148 @default.
- W4364305298 hasConcept C41065033 @default.
- W4364305298 hasConcept C86251818 @default.
- W4364305298 hasConceptScore W4364305298C105795698 @default.
- W4364305298 hasConceptScore W4364305298C119857082 @default.
- W4364305298 hasConceptScore W4364305298C127413603 @default.
- W4364305298 hasConceptScore W4364305298C144133560 @default.
- W4364305298 hasConceptScore W4364305298C153083717 @default.
- W4364305298 hasConceptScore W4364305298C154945302 @default.
- W4364305298 hasConceptScore W4364305298C162853370 @default.
- W4364305298 hasConceptScore W4364305298C22212356 @default.
- W4364305298 hasConceptScore W4364305298C27158222 @default.
- W4364305298 hasConceptScore W4364305298C2778403875 @default.
- W4364305298 hasConceptScore W4364305298C3018391801 @default.
- W4364305298 hasConceptScore W4364305298C33923547 @default.
- W4364305298 hasConceptScore W4364305298C37736160 @default.
- W4364305298 hasConceptScore W4364305298C38652104 @default.
- W4364305298 hasConceptScore W4364305298C41008148 @default.
- W4364305298 hasConceptScore W4364305298C41065033 @default.
- W4364305298 hasConceptScore W4364305298C86251818 @default.
- W4364305298 hasLocation W43643052981 @default.
- W4364305298 hasOpenAccess W4364305298 @default.
- W4364305298 hasPrimaryLocation W43643052981 @default.
- W4364305298 hasRelatedWork W2095577883 @default.
- W4364305298 hasRelatedWork W2571710472 @default.
- W4364305298 hasRelatedWork W2585881251 @default.
- W4364305298 hasRelatedWork W2953920146 @default.
- W4364305298 hasRelatedWork W3013617128 @default.
- W4364305298 hasRelatedWork W3124408655 @default.
- W4364305298 hasRelatedWork W4248052496 @default.
- W4364305298 hasRelatedWork W4251088474 @default.
- W4364305298 hasRelatedWork W4297785512 @default.
- W4364305298 hasRelatedWork W4298096631 @default.
- W4364305298 isParatext "false" @default.
- W4364305298 isRetracted "false" @default.
- W4364305298 workType "article" @default.