Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016101097> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3016101097 abstract "In recent times, deep neural networks have seen increased adoption in highly critical tasks. They are also susceptible to adversarial attacks, which are specifically crafted changes made to input samples which lead to erroneous output from such models. Such attacks have been shown to affect different types of data such as images and more recently, time-series data. Such susceptibility could have catastrophic consequences, depending on the domain.We propose a method for detecting Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM) adversarial attacks as adapted for time-series data. We frame the problem as an instance of outlier detection and construct a normalcy model based on information and chaos-theoretic measures, which can then be used to determine whether unseen samples are normal or adversarial. Our approach shows promising performance on several datasets from the 2015 UCR Time Series Archive, reaching up to 97% detection accuracy in the best case." @default.
- W3016101097 created "2020-04-17" @default.
- W3016101097 creator A5010680369 @default.
- W3016101097 creator A5040773064 @default.
- W3016101097 creator A5045053868 @default.
- W3016101097 creator A5066618929 @default.
- W3016101097 date "2020-05-01" @default.
- W3016101097 modified "2023-10-14" @default.
- W3016101097 title "Detecting Adversarial Attacks In Time-Series Data" @default.
- W3016101097 cites W1862394037 @default.
- W3016101097 cites W2017821362 @default.
- W3016101097 cites W2132870739 @default.
- W3016101097 cites W2161381512 @default.
- W3016101097 cites W2603766943 @default.
- W3016101097 cites W2968323358 @default.
- W3016101097 cites W2968356384 @default.
- W3016101097 cites W2968950625 @default.
- W3016101097 cites W2988138047 @default.
- W3016101097 cites W3105599650 @default.
- W3016101097 doi "https://doi.org/10.1109/icassp40776.2020.9053311" @default.
- W3016101097 hasPublicationYear "2020" @default.
- W3016101097 type Work @default.
- W3016101097 sameAs 3016101097 @default.
- W3016101097 citedByCount "7" @default.
- W3016101097 countsByYear W30161010972021 @default.
- W3016101097 countsByYear W30161010972022 @default.
- W3016101097 countsByYear W30161010972023 @default.
- W3016101097 crossrefType "proceedings-article" @default.
- W3016101097 hasAuthorship W3016101097A5010680369 @default.
- W3016101097 hasAuthorship W3016101097A5040773064 @default.
- W3016101097 hasAuthorship W3016101097A5045053868 @default.
- W3016101097 hasAuthorship W3016101097A5066618929 @default.
- W3016101097 hasConcept C119857082 @default.
- W3016101097 hasConcept C124101348 @default.
- W3016101097 hasConcept C126042441 @default.
- W3016101097 hasConcept C134306372 @default.
- W3016101097 hasConcept C143724316 @default.
- W3016101097 hasConcept C151406439 @default.
- W3016101097 hasConcept C151730666 @default.
- W3016101097 hasConcept C153180895 @default.
- W3016101097 hasConcept C154945302 @default.
- W3016101097 hasConcept C199360897 @default.
- W3016101097 hasConcept C2780801425 @default.
- W3016101097 hasConcept C33923547 @default.
- W3016101097 hasConcept C36503486 @default.
- W3016101097 hasConcept C37736160 @default.
- W3016101097 hasConcept C41008148 @default.
- W3016101097 hasConcept C739882 @default.
- W3016101097 hasConcept C76155785 @default.
- W3016101097 hasConcept C79337645 @default.
- W3016101097 hasConcept C86803240 @default.
- W3016101097 hasConceptScore W3016101097C119857082 @default.
- W3016101097 hasConceptScore W3016101097C124101348 @default.
- W3016101097 hasConceptScore W3016101097C126042441 @default.
- W3016101097 hasConceptScore W3016101097C134306372 @default.
- W3016101097 hasConceptScore W3016101097C143724316 @default.
- W3016101097 hasConceptScore W3016101097C151406439 @default.
- W3016101097 hasConceptScore W3016101097C151730666 @default.
- W3016101097 hasConceptScore W3016101097C153180895 @default.
- W3016101097 hasConceptScore W3016101097C154945302 @default.
- W3016101097 hasConceptScore W3016101097C199360897 @default.
- W3016101097 hasConceptScore W3016101097C2780801425 @default.
- W3016101097 hasConceptScore W3016101097C33923547 @default.
- W3016101097 hasConceptScore W3016101097C36503486 @default.
- W3016101097 hasConceptScore W3016101097C37736160 @default.
- W3016101097 hasConceptScore W3016101097C41008148 @default.
- W3016101097 hasConceptScore W3016101097C739882 @default.
- W3016101097 hasConceptScore W3016101097C76155785 @default.
- W3016101097 hasConceptScore W3016101097C79337645 @default.
- W3016101097 hasConceptScore W3016101097C86803240 @default.
- W3016101097 hasLocation W30161010971 @default.
- W3016101097 hasOpenAccess W3016101097 @default.
- W3016101097 hasPrimaryLocation W30161010971 @default.
- W3016101097 hasRelatedWork W190094394 @default.
- W3016101097 hasRelatedWork W2238926016 @default.
- W3016101097 hasRelatedWork W2360427278 @default.
- W3016101097 hasRelatedWork W2613265192 @default.
- W3016101097 hasRelatedWork W2741652912 @default.
- W3016101097 hasRelatedWork W2823903596 @default.
- W3016101097 hasRelatedWork W2920254490 @default.
- W3016101097 hasRelatedWork W3093575099 @default.
- W3016101097 hasRelatedWork W3106602985 @default.
- W3016101097 hasRelatedWork W4210448235 @default.
- W3016101097 isParatext "false" @default.
- W3016101097 isRetracted "false" @default.
- W3016101097 magId "3016101097" @default.
- W3016101097 workType "article" @default.