Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311159382> ?p ?o ?g. }
- W4311159382 endingPage "48" @default.
- W4311159382 startingPage "1" @default.
- W4311159382 abstract "Testing deep neural networks (DNNs) has garnered great interest in the recent years due to their use in many applications. Black-box test adequacy measures are useful for guiding the testing process in covering the input domain. However, the absence of input specifications makes it challenging to apply black-box test adequacy measures in DNN testing. The Input Distribution Coverage (IDC) framework addresses this challenge by using a variational autoencoder to learn a low dimensional latent representation of the input distribution, and then using that latent space as a coverage domain for testing. IDC applies combinatorial interaction testing on a partitioning of the latent space to measure test adequacy. Empirical evaluation demonstrates that IDC is cost-effective, capable of detecting feature diversity in test inputs, and more sensitive than prior work to test inputs generated using different DNN test generation methods. The findings demonstrate that IDC overcomes several limitations of white-box DNN coverage approaches by discounting coverage from unrealistic inputs and enabling the calculation of test adequacy metrics that capture the feature diversity present in the input space of DNNs." @default.
- W4311159382 created "2022-12-24" @default.
- W4311159382 creator A5039011377 @default.
- W4311159382 creator A5047746948 @default.
- W4311159382 creator A5086757331 @default.
- W4311159382 date "2023-04-26" @default.
- W4311159382 modified "2023-09-25" @default.
- W4311159382 title "Input Distribution Coverage: Measuring Feature Interaction Adequacy in Neural Network Testing" @default.
- W4311159382 cites W1834627138 @default.
- W4311159382 cites W1987220198 @default.
- W4311159382 cites W1992639336 @default.
- W4311159382 cites W2027106228 @default.
- W4311159382 cites W2065684071 @default.
- W4311159382 cites W2080718476 @default.
- W4311159382 cites W2099645986 @default.
- W4311159382 cites W2102742419 @default.
- W4311159382 cites W2108598243 @default.
- W4311159382 cites W2112796928 @default.
- W4311159382 cites W2122796178 @default.
- W4311159382 cites W2128204165 @default.
- W4311159382 cites W2133665775 @default.
- W4311159382 cites W2151103935 @default.
- W4311159382 cites W2162200351 @default.
- W4311159382 cites W2171570823 @default.
- W4311159382 cites W2194775991 @default.
- W4311159382 cites W2242375434 @default.
- W4311159382 cites W2304387544 @default.
- W4311159382 cites W2616028256 @default.
- W4311159382 cites W2802132828 @default.
- W4311159382 cites W2886698796 @default.
- W4311159382 cites W2888824816 @default.
- W4311159382 cites W2962770929 @default.
- W4311159382 cites W2963208512 @default.
- W4311159382 cites W2963327228 @default.
- W4311159382 cites W2963693826 @default.
- W4311159382 cites W2963913218 @default.
- W4311159382 cites W2964231450 @default.
- W4311159382 cites W2979485058 @default.
- W4311159382 cites W2994987245 @default.
- W4311159382 cites W3036286896 @default.
- W4311159382 cites W3089172967 @default.
- W4311159382 cites W3090643686 @default.
- W4311159382 cites W3099444373 @default.
- W4311159382 cites W3105249702 @default.
- W4311159382 cites W3105662466 @default.
- W4311159382 cites W3125205424 @default.
- W4311159382 cites W3163879210 @default.
- W4311159382 cites W3178469298 @default.
- W4311159382 cites W3178701007 @default.
- W4311159382 cites W3181437774 @default.
- W4311159382 cites W3185950485 @default.
- W4311159382 cites W3200467243 @default.
- W4311159382 cites W4238956019 @default.
- W4311159382 doi "https://doi.org/10.1145/3576040" @default.
- W4311159382 hasPublicationYear "2023" @default.
- W4311159382 type Work @default.
- W4311159382 citedByCount "0" @default.
- W4311159382 crossrefType "journal-article" @default.
- W4311159382 hasAuthorship W4311159382A5039011377 @default.
- W4311159382 hasAuthorship W4311159382A5047746948 @default.
- W4311159382 hasAuthorship W4311159382A5086757331 @default.
- W4311159382 hasBestOaLocation W43111593821 @default.
- W4311159382 hasConcept C101738243 @default.
- W4311159382 hasConcept C119857082 @default.
- W4311159382 hasConcept C124101348 @default.
- W4311159382 hasConcept C138885662 @default.
- W4311159382 hasConcept C149091818 @default.
- W4311159382 hasConcept C154945302 @default.
- W4311159382 hasConcept C158324730 @default.
- W4311159382 hasConcept C186846655 @default.
- W4311159382 hasConcept C199360897 @default.
- W4311159382 hasConcept C2776401178 @default.
- W4311159382 hasConcept C2777904410 @default.
- W4311159382 hasConcept C41008148 @default.
- W4311159382 hasConcept C41895202 @default.
- W4311159382 hasConcept C50644808 @default.
- W4311159382 hasConcept C53942775 @default.
- W4311159382 hasConcept C94966114 @default.
- W4311159382 hasConceptScore W4311159382C101738243 @default.
- W4311159382 hasConceptScore W4311159382C119857082 @default.
- W4311159382 hasConceptScore W4311159382C124101348 @default.
- W4311159382 hasConceptScore W4311159382C138885662 @default.
- W4311159382 hasConceptScore W4311159382C149091818 @default.
- W4311159382 hasConceptScore W4311159382C154945302 @default.
- W4311159382 hasConceptScore W4311159382C158324730 @default.
- W4311159382 hasConceptScore W4311159382C186846655 @default.
- W4311159382 hasConceptScore W4311159382C199360897 @default.
- W4311159382 hasConceptScore W4311159382C2776401178 @default.
- W4311159382 hasConceptScore W4311159382C2777904410 @default.
- W4311159382 hasConceptScore W4311159382C41008148 @default.
- W4311159382 hasConceptScore W4311159382C41895202 @default.
- W4311159382 hasConceptScore W4311159382C50644808 @default.
- W4311159382 hasConceptScore W4311159382C53942775 @default.
- W4311159382 hasConceptScore W4311159382C94966114 @default.
- W4311159382 hasFunder F4320338279 @default.
- W4311159382 hasIssue "3" @default.
- W4311159382 hasLocation W43111593821 @default.
- W4311159382 hasOpenAccess W4311159382 @default.