Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891797126> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2891797126 endingPage "234" @default.
- W2891797126 startingPage "211" @default.
- W2891797126 abstract "Machine learning has been applied in various information systems, but its vulnerability has not been well understood yet. This chapter studies vulnerability to adversarial machine learning in information systems such as online services with interfaces that accept user data inputs and return machine learning results such as labels. Two types of attacks are considered: exploratory (or inference) attack and evasion attack. In an exploratory attack, the adversary collects labels of input data from an online classifier and applies deep learning to train a functionally equivalent classifier without knowing the inner working of the target classifier. The vulnerability includes the theft of intellectual property (quantified by the statistical similarity of the target and inferred classifiers) and the support of other attacks built upon the inference results. An example of follow-up attacks is the evasion attack, where the adversary deceives the classifier into misclassifying input data samples that are systematically selected based on the classification scores from the inferred classier. This attack is strengthened by generative adversarial networks (GANs) and adversarial perturbations producing synthetic data samples that are likely to be misclassified. The vulnerability is measured by the increase in misdetection rates. This quantitative understanding of the vulnerability in machine learning systems provides valuable insights into designing defence mechanisms against adversarial machine learning." @default.
- W2891797126 created "2018-09-27" @default.
- W2891797126 creator A5054863127 @default.
- W2891797126 creator A5064001713 @default.
- W2891797126 creator A5075960743 @default.
- W2891797126 creator A5089570143 @default.
- W2891797126 date "2018-01-01" @default.
- W2891797126 modified "2023-10-16" @default.
- W2891797126 title "Vulnerability Detection and Analysis in Adversarial Deep Learning" @default.
- W2891797126 cites W1932198206 @default.
- W2891797126 cites W2005299943 @default.
- W2891797126 cites W2051267297 @default.
- W2891797126 cites W2064675550 @default.
- W2891797126 cites W2071707134 @default.
- W2891797126 cites W2095577883 @default.
- W2891797126 cites W2103496339 @default.
- W2891797126 cites W2124415900 @default.
- W2891797126 cites W2137983211 @default.
- W2891797126 cites W2151298633 @default.
- W2891797126 cites W2180612164 @default.
- W2891797126 cites W2211948716 @default.
- W2891797126 cites W2243397390 @default.
- W2891797126 cites W2257979135 @default.
- W2891797126 cites W2603766943 @default.
- W2891797126 cites W2610603914 @default.
- W2891797126 cites W2623427976 @default.
- W2891797126 cites W2766736793 @default.
- W2891797126 cites W2773459750 @default.
- W2891797126 cites W2853090665 @default.
- W2891797126 cites W2962835266 @default.
- W2891797126 cites W2963079272 @default.
- W2891797126 cites W9657784 @default.
- W2891797126 doi "https://doi.org/10.1007/978-3-319-92624-7_9" @default.
- W2891797126 hasPublicationYear "2018" @default.
- W2891797126 type Work @default.
- W2891797126 sameAs 2891797126 @default.
- W2891797126 citedByCount "10" @default.
- W2891797126 countsByYear W28917971262019 @default.
- W2891797126 countsByYear W28917971262020 @default.
- W2891797126 countsByYear W28917971262021 @default.
- W2891797126 countsByYear W28917971262023 @default.
- W2891797126 crossrefType "book-chapter" @default.
- W2891797126 hasAuthorship W2891797126A5054863127 @default.
- W2891797126 hasAuthorship W2891797126A5064001713 @default.
- W2891797126 hasAuthorship W2891797126A5075960743 @default.
- W2891797126 hasAuthorship W2891797126A5089570143 @default.
- W2891797126 hasConcept C119857082 @default.
- W2891797126 hasConcept C137176749 @default.
- W2891797126 hasConcept C154945302 @default.
- W2891797126 hasConcept C15744967 @default.
- W2891797126 hasConcept C167063184 @default.
- W2891797126 hasConcept C2776214188 @default.
- W2891797126 hasConcept C2778403875 @default.
- W2891797126 hasConcept C37736160 @default.
- W2891797126 hasConcept C38652104 @default.
- W2891797126 hasConcept C39890363 @default.
- W2891797126 hasConcept C41008148 @default.
- W2891797126 hasConcept C41065033 @default.
- W2891797126 hasConcept C542102704 @default.
- W2891797126 hasConcept C95623464 @default.
- W2891797126 hasConcept C95713431 @default.
- W2891797126 hasConceptScore W2891797126C119857082 @default.
- W2891797126 hasConceptScore W2891797126C137176749 @default.
- W2891797126 hasConceptScore W2891797126C154945302 @default.
- W2891797126 hasConceptScore W2891797126C15744967 @default.
- W2891797126 hasConceptScore W2891797126C167063184 @default.
- W2891797126 hasConceptScore W2891797126C2776214188 @default.
- W2891797126 hasConceptScore W2891797126C2778403875 @default.
- W2891797126 hasConceptScore W2891797126C37736160 @default.
- W2891797126 hasConceptScore W2891797126C38652104 @default.
- W2891797126 hasConceptScore W2891797126C39890363 @default.
- W2891797126 hasConceptScore W2891797126C41008148 @default.
- W2891797126 hasConceptScore W2891797126C41065033 @default.
- W2891797126 hasConceptScore W2891797126C542102704 @default.
- W2891797126 hasConceptScore W2891797126C95623464 @default.
- W2891797126 hasConceptScore W2891797126C95713431 @default.
- W2891797126 hasLocation W28917971261 @default.
- W2891797126 hasOpenAccess W2891797126 @default.
- W2891797126 hasPrimaryLocation W28917971261 @default.
- W2891797126 hasRelatedWork W141916771 @default.
- W2891797126 hasRelatedWork W2974723675 @default.
- W2891797126 hasRelatedWork W3013617128 @default.
- W2891797126 hasRelatedWork W3034953030 @default.
- W2891797126 hasRelatedWork W3124408655 @default.
- W2891797126 hasRelatedWork W3205128835 @default.
- W2891797126 hasRelatedWork W4248052496 @default.
- W2891797126 hasRelatedWork W4251088474 @default.
- W2891797126 hasRelatedWork W4286899967 @default.
- W2891797126 hasRelatedWork W4297785512 @default.
- W2891797126 isParatext "false" @default.
- W2891797126 isRetracted "false" @default.
- W2891797126 magId "2891797126" @default.
- W2891797126 workType "book-chapter" @default.