Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386908079> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4386908079 abstract "Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce underline{Rob}ust underline{in}terpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA." @default.
- W4386908079 created "2023-09-21" @default.
- W4386908079 creator A5010444377 @default.
- W4386908079 creator A5019179799 @default.
- W4386908079 creator A5022262922 @default.
- W4386908079 creator A5043839950 @default.
- W4386908079 creator A5063253432 @default.
- W4386908079 creator A5065037360 @default.
- W4386908079 creator A5074676946 @default.
- W4386908079 creator A5082079047 @default.
- W4386908079 date "2023-09-19" @default.
- W4386908079 modified "2023-09-28" @default.
- W4386908079 title "Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers" @default.
- W4386908079 doi "https://doi.org/10.48550/arxiv.2309.10644" @default.
- W4386908079 hasPublicationYear "2023" @default.
- W4386908079 type Work @default.
- W4386908079 citedByCount "0" @default.
- W4386908079 crossrefType "posted-content" @default.
- W4386908079 hasAuthorship W4386908079A5010444377 @default.
- W4386908079 hasAuthorship W4386908079A5019179799 @default.
- W4386908079 hasAuthorship W4386908079A5022262922 @default.
- W4386908079 hasAuthorship W4386908079A5043839950 @default.
- W4386908079 hasAuthorship W4386908079A5063253432 @default.
- W4386908079 hasAuthorship W4386908079A5065037360 @default.
- W4386908079 hasAuthorship W4386908079A5074676946 @default.
- W4386908079 hasAuthorship W4386908079A5082079047 @default.
- W4386908079 hasBestOaLocation W43869080791 @default.
- W4386908079 hasConcept C108583219 @default.
- W4386908079 hasConcept C119857082 @default.
- W4386908079 hasConcept C122783720 @default.
- W4386908079 hasConcept C154945302 @default.
- W4386908079 hasConcept C199360897 @default.
- W4386908079 hasConcept C2776459999 @default.
- W4386908079 hasConcept C2781067378 @default.
- W4386908079 hasConcept C41008148 @default.
- W4386908079 hasConcept C43126263 @default.
- W4386908079 hasConcept C76155785 @default.
- W4386908079 hasConcept C95623464 @default.
- W4386908079 hasConceptScore W4386908079C108583219 @default.
- W4386908079 hasConceptScore W4386908079C119857082 @default.
- W4386908079 hasConceptScore W4386908079C122783720 @default.
- W4386908079 hasConceptScore W4386908079C154945302 @default.
- W4386908079 hasConceptScore W4386908079C199360897 @default.
- W4386908079 hasConceptScore W4386908079C2776459999 @default.
- W4386908079 hasConceptScore W4386908079C2781067378 @default.
- W4386908079 hasConceptScore W4386908079C41008148 @default.
- W4386908079 hasConceptScore W4386908079C43126263 @default.
- W4386908079 hasConceptScore W4386908079C76155785 @default.
- W4386908079 hasConceptScore W4386908079C95623464 @default.
- W4386908079 hasLocation W43869080791 @default.
- W4386908079 hasOpenAccess W4386908079 @default.
- W4386908079 hasPrimaryLocation W43869080791 @default.
- W4386908079 hasRelatedWork W3006943036 @default.
- W4386908079 hasRelatedWork W3129898729 @default.
- W4386908079 hasRelatedWork W4206534706 @default.
- W4386908079 hasRelatedWork W4229079080 @default.
- W4386908079 hasRelatedWork W4299487748 @default.
- W4386908079 hasRelatedWork W4310880831 @default.
- W4386908079 hasRelatedWork W4380075502 @default.
- W4386908079 hasRelatedWork W4385957992 @default.
- W4386908079 hasRelatedWork W4385965371 @default.
- W4386908079 hasRelatedWork W4386025632 @default.
- W4386908079 isParatext "false" @default.
- W4386908079 isRetracted "false" @default.
- W4386908079 workType "article" @default.