Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327522024> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4327522024 endingPage "12" @default.
- W4327522024 startingPage "1" @default.
- W4327522024 abstract "While the data-driven fault classification systems have achieved great success and been widely deployed, machine-learning-based models have recently been shown to be unsafe and vulnerable to tiny perturbations, i.e., adversarial attack. For the safety-critical industrial scenarios, the adversarial security (i.e., adversarial robustness) of the fault system should be taken into serious consideration. However, security and accuracy are intrinsically conflicting, which is a trade-off issue. In this article, we first study this new trade-off issue in the design of fault classification models and solve it from a brand new view, hyperparameter optimization (HPO). Meanwhile, to reduce the computational expense of HPO, we propose a new multiobjective (MO), multifidelity (MF) Bayesian optimization (BO) algorithm, MMTPE. The proposed algorithm is evaluated on safety-critical industrial datasets with the mainstream machine learning (ML) models. The results show that the following hold: 1) MMTPE is superior to other advanced optimization algorithms in both efficiency and performance and 2) fault classification models with optimized hyperparameters are competitive with advanced adversarially defensive methods. Moreover, insights into the model security are given, including the model intrinsic security properties and the correlations between hyperparameters and security." @default.
- W4327522024 created "2023-03-17" @default.
- W4327522024 creator A5039062929 @default.
- W4327522024 creator A5049768588 @default.
- W4327522024 creator A5067726465 @default.
- W4327522024 date "2023-01-01" @default.
- W4327522024 modified "2023-10-12" @default.
- W4327522024 title "Security Versus Accuracy: Trade-Off Data Modeling to Safe Fault Classification Systems" @default.
- W4327522024 doi "https://doi.org/10.1109/tnnls.2023.3251999" @default.
- W4327522024 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37028378" @default.
- W4327522024 hasPublicationYear "2023" @default.
- W4327522024 type Work @default.
- W4327522024 citedByCount "0" @default.
- W4327522024 crossrefType "journal-article" @default.
- W4327522024 hasAuthorship W4327522024A5039062929 @default.
- W4327522024 hasAuthorship W4327522024A5049768588 @default.
- W4327522024 hasAuthorship W4327522024A5067726465 @default.
- W4327522024 hasConcept C104317684 @default.
- W4327522024 hasConcept C119857082 @default.
- W4327522024 hasConcept C124101348 @default.
- W4327522024 hasConcept C154945302 @default.
- W4327522024 hasConcept C163707989 @default.
- W4327522024 hasConcept C185592680 @default.
- W4327522024 hasConcept C199360897 @default.
- W4327522024 hasConcept C2777904410 @default.
- W4327522024 hasConcept C2778049539 @default.
- W4327522024 hasConcept C37736160 @default.
- W4327522024 hasConcept C41008148 @default.
- W4327522024 hasConcept C55493867 @default.
- W4327522024 hasConcept C63479239 @default.
- W4327522024 hasConcept C8642999 @default.
- W4327522024 hasConceptScore W4327522024C104317684 @default.
- W4327522024 hasConceptScore W4327522024C119857082 @default.
- W4327522024 hasConceptScore W4327522024C124101348 @default.
- W4327522024 hasConceptScore W4327522024C154945302 @default.
- W4327522024 hasConceptScore W4327522024C163707989 @default.
- W4327522024 hasConceptScore W4327522024C185592680 @default.
- W4327522024 hasConceptScore W4327522024C199360897 @default.
- W4327522024 hasConceptScore W4327522024C2777904410 @default.
- W4327522024 hasConceptScore W4327522024C2778049539 @default.
- W4327522024 hasConceptScore W4327522024C37736160 @default.
- W4327522024 hasConceptScore W4327522024C41008148 @default.
- W4327522024 hasConceptScore W4327522024C55493867 @default.
- W4327522024 hasConceptScore W4327522024C63479239 @default.
- W4327522024 hasConceptScore W4327522024C8642999 @default.
- W4327522024 hasFunder F4320321001 @default.
- W4327522024 hasFunder F4320338464 @default.
- W4327522024 hasLocation W43275220241 @default.
- W4327522024 hasLocation W43275220242 @default.
- W4327522024 hasOpenAccess W4327522024 @default.
- W4327522024 hasPrimaryLocation W43275220241 @default.
- W4327522024 hasRelatedWork W2200000192 @default.
- W4327522024 hasRelatedWork W2405673391 @default.
- W4327522024 hasRelatedWork W2408019865 @default.
- W4327522024 hasRelatedWork W2782093256 @default.
- W4327522024 hasRelatedWork W2963474950 @default.
- W4327522024 hasRelatedWork W3155731460 @default.
- W4327522024 hasRelatedWork W3198858656 @default.
- W4327522024 hasRelatedWork W3199608561 @default.
- W4327522024 hasRelatedWork W3214139057 @default.
- W4327522024 hasRelatedWork W4327522024 @default.
- W4327522024 isParatext "false" @default.
- W4327522024 isRetracted "false" @default.
- W4327522024 workType "article" @default.