Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091102523> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3091102523 abstract "Software composition analysis depends on database of open-source library vulerabilities, curated by security researchers using various sources, such as bug tracking systems, commits, and mailing lists. We report the design and implementation of a machine learning system to help the curation by by automatically predicting the vulnerability-relatedness of each data item. It supports a complete pipeline from data collection, model training and prediction, to the validation of new models before deployment. It is executed iteratively to generate better models as new input data become available. We use self-training to significantly and automatically increase the size of the training dataset, opportunistically maximizing the improvement in the models' quality at each iteration. We devised new deployment stability metric to evaluate the quality of the new models before deployment into production, which helped to discover an error. We experimentally evaluate the improvement in the performance of the models in one iteration, with 27.59% maximum PR AUC improvements. Ours is the first of such study across a variety of data sources. We discover that the addition of the features of the corresponding commits to the features of issues/pull requests improve the precision for the recall values that matter. We demonstrate the effectiveness of self-training alone, with 10.50% PR AUC improvement, and we discover that there is no uniform ordering of word2vec parameters sensitivity across data sources." @default.
- W3091102523 created "2020-10-08" @default.
- W3091102523 creator A5013712945 @default.
- W3091102523 creator A5015350971 @default.
- W3091102523 creator A5020819058 @default.
- W3091102523 creator A5048346296 @default.
- W3091102523 creator A5053535809 @default.
- W3091102523 creator A5081036622 @default.
- W3091102523 date "2020-06-29" @default.
- W3091102523 modified "2023-10-16" @default.
- W3091102523 title "A Machine Learning Approach for Vulnerability Curation" @default.
- W3091102523 cites W1479807131 @default.
- W3091102523 cites W1965895350 @default.
- W3091102523 cites W2003315002 @default.
- W3091102523 cites W2015452969 @default.
- W3091102523 cites W2037603696 @default.
- W3091102523 cites W2048679005 @default.
- W3091102523 cites W2069268700 @default.
- W3091102523 cites W2079057609 @default.
- W3091102523 cites W2118978333 @default.
- W3091102523 cites W2120457925 @default.
- W3091102523 cites W2137952932 @default.
- W3091102523 cites W2297419069 @default.
- W3091102523 cites W2562319768 @default.
- W3091102523 cites W2740329368 @default.
- W3091102523 cites W2748690817 @default.
- W3091102523 cites W2962698568 @default.
- W3091102523 cites W2962739339 @default.
- W3091102523 cites W3102476541 @default.
- W3091102523 cites W3142656464 @default.
- W3091102523 doi "https://doi.org/10.1145/3379597.3387461" @default.
- W3091102523 hasPublicationYear "2020" @default.
- W3091102523 type Work @default.
- W3091102523 sameAs 3091102523 @default.
- W3091102523 citedByCount "19" @default.
- W3091102523 countsByYear W30911025232021 @default.
- W3091102523 countsByYear W30911025232022 @default.
- W3091102523 countsByYear W30911025232023 @default.
- W3091102523 crossrefType "proceedings-article" @default.
- W3091102523 hasAuthorship W3091102523A5013712945 @default.
- W3091102523 hasAuthorship W3091102523A5015350971 @default.
- W3091102523 hasAuthorship W3091102523A5020819058 @default.
- W3091102523 hasAuthorship W3091102523A5048346296 @default.
- W3091102523 hasAuthorship W3091102523A5053535809 @default.
- W3091102523 hasAuthorship W3091102523A5081036622 @default.
- W3091102523 hasBestOaLocation W30911025232 @default.
- W3091102523 hasConcept C119857082 @default.
- W3091102523 hasConcept C137176749 @default.
- W3091102523 hasConcept C154945302 @default.
- W3091102523 hasConcept C15744967 @default.
- W3091102523 hasConcept C167063184 @default.
- W3091102523 hasConcept C2522767166 @default.
- W3091102523 hasConcept C38652104 @default.
- W3091102523 hasConcept C41008148 @default.
- W3091102523 hasConcept C542102704 @default.
- W3091102523 hasConcept C91632574 @default.
- W3091102523 hasConcept C95713431 @default.
- W3091102523 hasConceptScore W3091102523C119857082 @default.
- W3091102523 hasConceptScore W3091102523C137176749 @default.
- W3091102523 hasConceptScore W3091102523C154945302 @default.
- W3091102523 hasConceptScore W3091102523C15744967 @default.
- W3091102523 hasConceptScore W3091102523C167063184 @default.
- W3091102523 hasConceptScore W3091102523C2522767166 @default.
- W3091102523 hasConceptScore W3091102523C38652104 @default.
- W3091102523 hasConceptScore W3091102523C41008148 @default.
- W3091102523 hasConceptScore W3091102523C542102704 @default.
- W3091102523 hasConceptScore W3091102523C91632574 @default.
- W3091102523 hasConceptScore W3091102523C95713431 @default.
- W3091102523 hasLocation W30911025231 @default.
- W3091102523 hasLocation W30911025232 @default.
- W3091102523 hasOpenAccess W3091102523 @default.
- W3091102523 hasPrimaryLocation W30911025231 @default.
- W3091102523 hasRelatedWork W1883246888 @default.
- W3091102523 hasRelatedWork W2379513284 @default.
- W3091102523 hasRelatedWork W2496978885 @default.
- W3091102523 hasRelatedWork W2900108648 @default.
- W3091102523 hasRelatedWork W2961085424 @default.
- W3091102523 hasRelatedWork W4286629047 @default.
- W3091102523 hasRelatedWork W4295181103 @default.
- W3091102523 hasRelatedWork W4306674287 @default.
- W3091102523 hasRelatedWork W44448598 @default.
- W3091102523 hasRelatedWork W4224009465 @default.
- W3091102523 isParatext "false" @default.
- W3091102523 isRetracted "false" @default.
- W3091102523 magId "3091102523" @default.
- W3091102523 workType "article" @default.