Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963784236> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2963784236 endingPage "2621" @default.
- W2963784236 startingPage "2613" @default.
- W2963784236 abstract "Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net and devise a novel algorithm for approximating these metrics based on an encoding of robustness as a linear program. We show how our metrics can be used to evaluate the robustness of deep neural nets with experiments on the MNIST and CIFAR-10 datasets. Our algorithm generates more informative estimates of robustness metrics compared to estimates based on existing algorithms. Furthermore, we show how existing approaches to improving robustness “overfit” to adversarial examples generated using a specific algorithm. Finally, we show that our techniques can be used to additionally improve neural net robustness both according to the metrics that we propose, but also according to previously proposed metrics." @default.
- W2963784236 created "2019-07-30" @default.
- W2963784236 creator A5004486211 @default.
- W2963784236 creator A5029108294 @default.
- W2963784236 creator A5029243071 @default.
- W2963784236 creator A5063025899 @default.
- W2963784236 creator A5075217645 @default.
- W2963784236 creator A5091150085 @default.
- W2963784236 date "2016-05-24" @default.
- W2963784236 modified "2023-09-29" @default.
- W2963784236 title "Measuring Neural Net Robustness with Constraints" @default.
- W2963784236 hasPublicationYear "2016" @default.
- W2963784236 type Work @default.
- W2963784236 sameAs 2963784236 @default.
- W2963784236 citedByCount "73" @default.
- W2963784236 countsByYear W29637842362017 @default.
- W2963784236 countsByYear W29637842362018 @default.
- W2963784236 countsByYear W29637842362019 @default.
- W2963784236 countsByYear W29637842362020 @default.
- W2963784236 countsByYear W29637842362021 @default.
- W2963784236 countsByYear W29637842362023 @default.
- W2963784236 crossrefType "proceedings-article" @default.
- W2963784236 hasAuthorship W2963784236A5004486211 @default.
- W2963784236 hasAuthorship W2963784236A5029108294 @default.
- W2963784236 hasAuthorship W2963784236A5029243071 @default.
- W2963784236 hasAuthorship W2963784236A5063025899 @default.
- W2963784236 hasAuthorship W2963784236A5075217645 @default.
- W2963784236 hasAuthorship W2963784236A5091150085 @default.
- W2963784236 hasConcept C104317684 @default.
- W2963784236 hasConcept C11413529 @default.
- W2963784236 hasConcept C119857082 @default.
- W2963784236 hasConcept C154945302 @default.
- W2963784236 hasConcept C185592680 @default.
- W2963784236 hasConcept C190502265 @default.
- W2963784236 hasConcept C22019652 @default.
- W2963784236 hasConcept C41008148 @default.
- W2963784236 hasConcept C50644808 @default.
- W2963784236 hasConcept C55493867 @default.
- W2963784236 hasConcept C63479239 @default.
- W2963784236 hasConceptScore W2963784236C104317684 @default.
- W2963784236 hasConceptScore W2963784236C11413529 @default.
- W2963784236 hasConceptScore W2963784236C119857082 @default.
- W2963784236 hasConceptScore W2963784236C154945302 @default.
- W2963784236 hasConceptScore W2963784236C185592680 @default.
- W2963784236 hasConceptScore W2963784236C190502265 @default.
- W2963784236 hasConceptScore W2963784236C22019652 @default.
- W2963784236 hasConceptScore W2963784236C41008148 @default.
- W2963784236 hasConceptScore W2963784236C50644808 @default.
- W2963784236 hasConceptScore W2963784236C55493867 @default.
- W2963784236 hasConceptScore W2963784236C63479239 @default.
- W2963784236 hasLocation W29637842361 @default.
- W2963784236 hasOpenAccess W2963784236 @default.
- W2963784236 hasPrimaryLocation W29637842361 @default.
- W2963784236 hasRelatedWork W1932198206 @default.
- W2963784236 hasRelatedWork W2163605009 @default.
- W2963784236 hasRelatedWork W2180612164 @default.
- W2963784236 hasRelatedWork W2194775991 @default.
- W2963784236 hasRelatedWork W2243397390 @default.
- W2963784236 hasRelatedWork W2543296129 @default.
- W2963784236 hasRelatedWork W2594877703 @default.
- W2963784236 hasRelatedWork W2616028256 @default.
- W2963784236 hasRelatedWork W2721006554 @default.
- W2963784236 hasRelatedWork W2794609696 @default.
- W2963784236 hasRelatedWork W2807040120 @default.
- W2963784236 hasRelatedWork W2963054787 @default.
- W2963784236 hasRelatedWork W2963207607 @default.
- W2963784236 hasRelatedWork W2963440492 @default.
- W2963784236 hasRelatedWork W2963496101 @default.
- W2963784236 hasRelatedWork W2963735478 @default.
- W2963784236 hasRelatedWork W2963857521 @default.
- W2963784236 hasRelatedWork W2964082701 @default.
- W2963784236 hasRelatedWork W2964153729 @default.
- W2963784236 hasRelatedWork W2964253222 @default.
- W2963784236 hasVolume "29" @default.
- W2963784236 isParatext "false" @default.
- W2963784236 isRetracted "false" @default.
- W2963784236 magId "2963784236" @default.
- W2963784236 workType "article" @default.