Matches in SemOpenAlex for { <https://semopenalex.org/work/W3000239664> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3000239664 abstract "Recurrent neural network (RNN) has achieved great success in processing sequential inputs for applications such as automatic speech recognition, natural language processing and machine translation. However, quality and reliability issues of RNNs make them vulnerable to adversarial attacks and hinder their deployment in real-world applications. In this paper, we propose a quantitative analysis framework - DeepStellar - to pave the way for effective quality and security analysis of software systems powered by RNNs. DeepStellar is generic to handle various RNN architectures, including LSTM and GRU, scalable to work on industrial-grade RNN models, and extensible to develop customized analyzers and tools. We demonstrated that, with DeepStellar, users are able to design efficient test generation tools, and develop effective adversarial sample detectors. We tested the developed applications on three real RNN models, including speech recognition and image classification. DeepStellar outperforms existing approaches three hundred times in generating defect-triggering tests and achieves 97% accuracy in detecting adversarial attacks. A video demonstration which shows the main features of DeepStellar is available at: https://sites.google.com/view/deepstellar/tool-demo." @default.
- W3000239664 created "2020-01-23" @default.
- W3000239664 creator A5002071885 @default.
- W3000239664 creator A5010478725 @default.
- W3000239664 creator A5064273534 @default.
- W3000239664 creator A5065190767 @default.
- W3000239664 creator A5070199660 @default.
- W3000239664 creator A5084396416 @default.
- W3000239664 date "2019-11-01" @default.
- W3000239664 modified "2023-09-23" @default.
- W3000239664 title "A Quantitative Analysis Framework for Recurrent Neural Network" @default.
- W3000239664 cites W1998937898 @default.
- W3000239664 cites W2064675550 @default.
- W3000239664 cites W2163022590 @default.
- W3000239664 cites W2616028256 @default.
- W3000239664 cites W2963327228 @default.
- W3000239664 cites W2964199361 @default.
- W3000239664 cites W2964301649 @default.
- W3000239664 cites W2964882141 @default.
- W3000239664 cites W2968940383 @default.
- W3000239664 cites W3000315285 @default.
- W3000239664 cites W3105599650 @default.
- W3000239664 doi "https://doi.org/10.1109/ase.2019.00102" @default.
- W3000239664 hasPublicationYear "2019" @default.
- W3000239664 type Work @default.
- W3000239664 sameAs 3000239664 @default.
- W3000239664 citedByCount "7" @default.
- W3000239664 countsByYear W30002396642020 @default.
- W3000239664 countsByYear W30002396642021 @default.
- W3000239664 countsByYear W30002396642022 @default.
- W3000239664 crossrefType "proceedings-article" @default.
- W3000239664 hasAuthorship W3000239664A5002071885 @default.
- W3000239664 hasAuthorship W3000239664A5010478725 @default.
- W3000239664 hasAuthorship W3000239664A5064273534 @default.
- W3000239664 hasAuthorship W3000239664A5065190767 @default.
- W3000239664 hasAuthorship W3000239664A5070199660 @default.
- W3000239664 hasAuthorship W3000239664A5084396416 @default.
- W3000239664 hasBestOaLocation W30002396642 @default.
- W3000239664 hasConcept C105339364 @default.
- W3000239664 hasConcept C115903868 @default.
- W3000239664 hasConcept C119857082 @default.
- W3000239664 hasConcept C121332964 @default.
- W3000239664 hasConcept C147168706 @default.
- W3000239664 hasConcept C154945302 @default.
- W3000239664 hasConcept C163258240 @default.
- W3000239664 hasConcept C203005215 @default.
- W3000239664 hasConcept C37736160 @default.
- W3000239664 hasConcept C41008148 @default.
- W3000239664 hasConcept C43214815 @default.
- W3000239664 hasConcept C48044578 @default.
- W3000239664 hasConcept C50644808 @default.
- W3000239664 hasConcept C62520636 @default.
- W3000239664 hasConcept C77088390 @default.
- W3000239664 hasConceptScore W3000239664C105339364 @default.
- W3000239664 hasConceptScore W3000239664C115903868 @default.
- W3000239664 hasConceptScore W3000239664C119857082 @default.
- W3000239664 hasConceptScore W3000239664C121332964 @default.
- W3000239664 hasConceptScore W3000239664C147168706 @default.
- W3000239664 hasConceptScore W3000239664C154945302 @default.
- W3000239664 hasConceptScore W3000239664C163258240 @default.
- W3000239664 hasConceptScore W3000239664C203005215 @default.
- W3000239664 hasConceptScore W3000239664C37736160 @default.
- W3000239664 hasConceptScore W3000239664C41008148 @default.
- W3000239664 hasConceptScore W3000239664C43214815 @default.
- W3000239664 hasConceptScore W3000239664C48044578 @default.
- W3000239664 hasConceptScore W3000239664C50644808 @default.
- W3000239664 hasConceptScore W3000239664C62520636 @default.
- W3000239664 hasConceptScore W3000239664C77088390 @default.
- W3000239664 hasLocation W30002396641 @default.
- W3000239664 hasLocation W30002396642 @default.
- W3000239664 hasOpenAccess W3000239664 @default.
- W3000239664 hasPrimaryLocation W30002396641 @default.
- W3000239664 hasRelatedWork W2344365922 @default.
- W3000239664 hasRelatedWork W2896411932 @default.
- W3000239664 hasRelatedWork W2963834268 @default.
- W3000239664 hasRelatedWork W3107474891 @default.
- W3000239664 hasRelatedWork W3202456239 @default.
- W3000239664 hasRelatedWork W4213142596 @default.
- W3000239664 hasRelatedWork W4281386417 @default.
- W3000239664 hasRelatedWork W4301957244 @default.
- W3000239664 hasRelatedWork W4312263439 @default.
- W3000239664 hasRelatedWork W1629725936 @default.
- W3000239664 isParatext "false" @default.
- W3000239664 isRetracted "false" @default.
- W3000239664 magId "3000239664" @default.
- W3000239664 workType "article" @default.