Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312323218> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4312323218 abstract "In this paper, we conduct a measurement study to comprehensively compare the accuracy of Cryptographic API completion tasks trained with multiple API embedding options. Embedding is the process of automatically learning to represent program elements as low-dimensional vectors. Our measurement aims to uncover the impacts of applying program analysis, token-level embedding, and sequence-level embedding on the Cryptographic API completion accuracies. Our findings show that program analysis is necessary even under advanced embedding. The results show 36.10% accuracy improvement on average when program analysis preprocessing is applied to transfer byte code sequences into API dependence paths. The best accuracy (93.52%) is achieved on API dependence paths with embedding techniques. On the contrary, the pure data-driven approach without program analysis only achieves a low accuracy (around 57.60%), even after the powerful sequence-level embedding is applied. Although sequence-level embedding shows slight accuracy advantages (0.55% on average) over token-level embedding in our basic data split setting, it is not recommended considering its expensive training cost. A more obvious accuracy improvement (5.10%) from sequence-level embedding is observed under the cross-project learning scenario when task data is insufficient. Hence, we recommend applying sequence-level embedding for cross-project learning with limited task-specific data." @default.
- W4312323218 created "2023-01-04" @default.
- W4312323218 creator A5022718146 @default.
- W4312323218 creator A5034366344 @default.
- W4312323218 creator A5047415405 @default.
- W4312323218 creator A5070152860 @default.
- W4312323218 creator A5081377370 @default.
- W4312323218 creator A5085945429 @default.
- W4312323218 date "2022-05-21" @default.
- W4312323218 modified "2023-10-16" @default.
- W4312323218 title "Comprehensive comparisons of embedding approaches for cryptographic API completion" @default.
- W4312323218 cites W2619465136 @default.
- W4312323218 cites W2759023773 @default.
- W4312323218 cites W2926178846 @default.
- W4312323218 cites W2963408280 @default.
- W4312323218 cites W2964150020 @default.
- W4312323218 cites W2985320478 @default.
- W4312323218 cites W3104712907 @default.
- W4312323218 doi "https://doi.org/10.1145/3510454.3528645" @default.
- W4312323218 hasPublicationYear "2022" @default.
- W4312323218 type Work @default.
- W4312323218 citedByCount "0" @default.
- W4312323218 crossrefType "proceedings-article" @default.
- W4312323218 hasAuthorship W4312323218A5022718146 @default.
- W4312323218 hasAuthorship W4312323218A5034366344 @default.
- W4312323218 hasAuthorship W4312323218A5047415405 @default.
- W4312323218 hasAuthorship W4312323218A5070152860 @default.
- W4312323218 hasAuthorship W4312323218A5081377370 @default.
- W4312323218 hasAuthorship W4312323218A5085945429 @default.
- W4312323218 hasBestOaLocation W43123232181 @default.
- W4312323218 hasConcept C11413529 @default.
- W4312323218 hasConcept C124101348 @default.
- W4312323218 hasConcept C127413603 @default.
- W4312323218 hasConcept C154945302 @default.
- W4312323218 hasConcept C178489894 @default.
- W4312323218 hasConcept C201995342 @default.
- W4312323218 hasConcept C2778112365 @default.
- W4312323218 hasConcept C2780451532 @default.
- W4312323218 hasConcept C34736171 @default.
- W4312323218 hasConcept C41008148 @default.
- W4312323218 hasConcept C41608201 @default.
- W4312323218 hasConcept C54355233 @default.
- W4312323218 hasConcept C80444323 @default.
- W4312323218 hasConcept C86803240 @default.
- W4312323218 hasConceptScore W4312323218C11413529 @default.
- W4312323218 hasConceptScore W4312323218C124101348 @default.
- W4312323218 hasConceptScore W4312323218C127413603 @default.
- W4312323218 hasConceptScore W4312323218C154945302 @default.
- W4312323218 hasConceptScore W4312323218C178489894 @default.
- W4312323218 hasConceptScore W4312323218C201995342 @default.
- W4312323218 hasConceptScore W4312323218C2778112365 @default.
- W4312323218 hasConceptScore W4312323218C2780451532 @default.
- W4312323218 hasConceptScore W4312323218C34736171 @default.
- W4312323218 hasConceptScore W4312323218C41008148 @default.
- W4312323218 hasConceptScore W4312323218C41608201 @default.
- W4312323218 hasConceptScore W4312323218C54355233 @default.
- W4312323218 hasConceptScore W4312323218C80444323 @default.
- W4312323218 hasConceptScore W4312323218C86803240 @default.
- W4312323218 hasFunder F4320306076 @default.
- W4312323218 hasLocation W43123232181 @default.
- W4312323218 hasOpenAccess W4312323218 @default.
- W4312323218 hasPrimaryLocation W43123232181 @default.
- W4312323218 hasRelatedWork W2055709700 @default.
- W4312323218 hasRelatedWork W2081647779 @default.
- W4312323218 hasRelatedWork W2108237372 @default.
- W4312323218 hasRelatedWork W2382928216 @default.
- W4312323218 hasRelatedWork W2384383430 @default.
- W4312323218 hasRelatedWork W2622473642 @default.
- W4312323218 hasRelatedWork W2783233264 @default.
- W4312323218 hasRelatedWork W2966686650 @default.
- W4312323218 hasRelatedWork W3107474891 @default.
- W4312323218 hasRelatedWork W4237750775 @default.
- W4312323218 isParatext "false" @default.
- W4312323218 isRetracted "false" @default.
- W4312323218 workType "article" @default.