Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783648986> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2783648986 abstract "Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples in perfect or limited knowledge setting using prior probability distributions on the defender's classifier. Using the asymptotic properties of the logistic regression, we derive a closed-form expression of the intensity of any adversarial perturbation, in order to achieve a given expected misclassification rate. This technique is relevant in a threat model of known model specifications and unknown training data. To our knowledge, this is the first method that allows an attacker to directly choose the probability of attack success. We evaluate our approach on two real-world datasets." @default.
- W2783648986 created "2018-01-26" @default.
- W2783648986 creator A5058150999 @default.
- W2783648986 date "2018-01-06" @default.
- W2783648986 modified "2023-09-27" @default.
- W2783648986 title "Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression" @default.
- W2783648986 cites W1528905581 @default.
- W2783648986 cites W1945616565 @default.
- W2783648986 cites W1990655238 @default.
- W2783648986 cites W2101234009 @default.
- W2783648986 cites W2106393550 @default.
- W2783648986 cites W2181523240 @default.
- W2783648986 cites W2243397390 @default.
- W2783648986 cites W2408141691 @default.
- W2783648986 cites W2603766943 @default.
- W2783648986 cites W2744095836 @default.
- W2783648986 cites W2773446523 @default.
- W2783648986 cites W2949152835 @default.
- W2783648986 cites W642783518 @default.
- W2783648986 cites W9657784 @default.
- W2783648986 hasPublicationYear "2018" @default.
- W2783648986 type Work @default.
- W2783648986 sameAs 2783648986 @default.
- W2783648986 citedByCount "0" @default.
- W2783648986 crossrefType "posted-content" @default.
- W2783648986 hasAuthorship W2783648986A5058150999 @default.
- W2783648986 hasConcept C119857082 @default.
- W2783648986 hasConcept C121332964 @default.
- W2783648986 hasConcept C12267149 @default.
- W2783648986 hasConcept C140331021 @default.
- W2783648986 hasConcept C151956035 @default.
- W2783648986 hasConcept C154945302 @default.
- W2783648986 hasConcept C177918212 @default.
- W2783648986 hasConcept C189119545 @default.
- W2783648986 hasConcept C37736160 @default.
- W2783648986 hasConcept C41008148 @default.
- W2783648986 hasConcept C49937458 @default.
- W2783648986 hasConcept C52001869 @default.
- W2783648986 hasConcept C61272859 @default.
- W2783648986 hasConcept C62520636 @default.
- W2783648986 hasConcept C95623464 @default.
- W2783648986 hasConceptScore W2783648986C119857082 @default.
- W2783648986 hasConceptScore W2783648986C121332964 @default.
- W2783648986 hasConceptScore W2783648986C12267149 @default.
- W2783648986 hasConceptScore W2783648986C140331021 @default.
- W2783648986 hasConceptScore W2783648986C151956035 @default.
- W2783648986 hasConceptScore W2783648986C154945302 @default.
- W2783648986 hasConceptScore W2783648986C177918212 @default.
- W2783648986 hasConceptScore W2783648986C189119545 @default.
- W2783648986 hasConceptScore W2783648986C37736160 @default.
- W2783648986 hasConceptScore W2783648986C41008148 @default.
- W2783648986 hasConceptScore W2783648986C49937458 @default.
- W2783648986 hasConceptScore W2783648986C52001869 @default.
- W2783648986 hasConceptScore W2783648986C61272859 @default.
- W2783648986 hasConceptScore W2783648986C62520636 @default.
- W2783648986 hasConceptScore W2783648986C95623464 @default.
- W2783648986 hasLocation W27836489861 @default.
- W2783648986 hasOpenAccess W2783648986 @default.
- W2783648986 hasPrimaryLocation W27836489861 @default.
- W2783648986 hasRelatedWork W1566807571 @default.
- W2783648986 hasRelatedWork W1579146157 @default.
- W2783648986 hasRelatedWork W1893233497 @default.
- W2783648986 hasRelatedWork W1994163801 @default.
- W2783648986 hasRelatedWork W2024971725 @default.
- W2783648986 hasRelatedWork W2062258832 @default.
- W2783648986 hasRelatedWork W2116650462 @default.
- W2783648986 hasRelatedWork W2388551560 @default.
- W2783648986 hasRelatedWork W2942547243 @default.
- W2783648986 hasRelatedWork W2959993158 @default.
- W2783648986 hasRelatedWork W2963015832 @default.
- W2783648986 hasRelatedWork W2990745812 @default.
- W2783648986 hasRelatedWork W3038062530 @default.
- W2783648986 hasRelatedWork W3113786991 @default.
- W2783648986 hasRelatedWork W3154290412 @default.
- W2783648986 hasRelatedWork W3172697571 @default.
- W2783648986 hasRelatedWork W3176418578 @default.
- W2783648986 hasRelatedWork W33163430 @default.
- W2783648986 hasRelatedWork W749362597 @default.
- W2783648986 hasRelatedWork W2152790647 @default.
- W2783648986 isParatext "false" @default.
- W2783648986 isRetracted "false" @default.
- W2783648986 magId "2783648986" @default.
- W2783648986 workType "article" @default.