Matches in SemOpenAlex for { <https://semopenalex.org/work/W2030611346> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2030611346 abstract "Adversarial learning is the study of machine learning techniques deployed in non-benign environments. Example applications include classifications for detecting spam email, network intrusion detection and credit card scoring. In fact as the gamut of application domains of machine learning grows, the possibility and opportunity for adversarial behavior will only increase. Till now, the standard assumption about modeling adversarial behavior has been to empower an adversary to change all features of the classifiers at will. The adversary pays a cost proportional to the size of attack. We refer to this form of adversarial behavior as a dense feature attack. However, the aim of an adversary is not just to subvert a classifier but carry out data transformation in a way such that spam continues to appear like spam to the user as much as possible. We demonstrate that an adversary achieves this objective by carrying out a sparse feature attack. We design an algorithm to show how a classifier should be designed to be robust against sparse adversarial attacks. Our main insight is that sparse feature attacks are best defended by designing classifiers which use ℓ <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sub> regularizers." @default.
- W2030611346 created "2016-06-24" @default.
- W2030611346 creator A5037947876 @default.
- W2030611346 creator A5071037763 @default.
- W2030611346 creator A5086529957 @default.
- W2030611346 date "2014-12-01" @default.
- W2030611346 modified "2023-10-17" @default.
- W2030611346 title "On Sparse Feature Attacks in Adversarial Learning" @default.
- W2030611346 cites W1965052658 @default.
- W2030611346 cites W1966912382 @default.
- W2030611346 cites W1990676004 @default.
- W2030611346 cites W1994520254 @default.
- W2030611346 cites W1996234057 @default.
- W2030611346 cites W2114296159 @default.
- W2030611346 cites W2117173631 @default.
- W2030611346 cites W2146211964 @default.
- W2030611346 cites W2293768274 @default.
- W2030611346 cites W2296452361 @default.
- W2030611346 cites W2401760721 @default.
- W2030611346 cites W2787894218 @default.
- W2030611346 doi "https://doi.org/10.1109/icdm.2014.117" @default.
- W2030611346 hasPublicationYear "2014" @default.
- W2030611346 type Work @default.
- W2030611346 sameAs 2030611346 @default.
- W2030611346 citedByCount "25" @default.
- W2030611346 countsByYear W20306113462015 @default.
- W2030611346 countsByYear W20306113462016 @default.
- W2030611346 countsByYear W20306113462017 @default.
- W2030611346 countsByYear W20306113462018 @default.
- W2030611346 countsByYear W20306113462019 @default.
- W2030611346 countsByYear W20306113462021 @default.
- W2030611346 countsByYear W20306113462022 @default.
- W2030611346 countsByYear W20306113462023 @default.
- W2030611346 crossrefType "proceedings-article" @default.
- W2030611346 hasAuthorship W2030611346A5037947876 @default.
- W2030611346 hasAuthorship W2030611346A5071037763 @default.
- W2030611346 hasAuthorship W2030611346A5086529957 @default.
- W2030611346 hasConcept C119857082 @default.
- W2030611346 hasConcept C138885662 @default.
- W2030611346 hasConcept C154945302 @default.
- W2030611346 hasConcept C2776401178 @default.
- W2030611346 hasConcept C35525427 @default.
- W2030611346 hasConcept C37736160 @default.
- W2030611346 hasConcept C38652104 @default.
- W2030611346 hasConcept C41008148 @default.
- W2030611346 hasConcept C41065033 @default.
- W2030611346 hasConcept C41895202 @default.
- W2030611346 hasConcept C95623464 @default.
- W2030611346 hasConceptScore W2030611346C119857082 @default.
- W2030611346 hasConceptScore W2030611346C138885662 @default.
- W2030611346 hasConceptScore W2030611346C154945302 @default.
- W2030611346 hasConceptScore W2030611346C2776401178 @default.
- W2030611346 hasConceptScore W2030611346C35525427 @default.
- W2030611346 hasConceptScore W2030611346C37736160 @default.
- W2030611346 hasConceptScore W2030611346C38652104 @default.
- W2030611346 hasConceptScore W2030611346C41008148 @default.
- W2030611346 hasConceptScore W2030611346C41065033 @default.
- W2030611346 hasConceptScore W2030611346C41895202 @default.
- W2030611346 hasConceptScore W2030611346C95623464 @default.
- W2030611346 hasLocation W20306113461 @default.
- W2030611346 hasOpenAccess W2030611346 @default.
- W2030611346 hasPrimaryLocation W20306113461 @default.
- W2030611346 hasRelatedWork W2460937040 @default.
- W2030611346 hasRelatedWork W2522301850 @default.
- W2030611346 hasRelatedWork W2952541330 @default.
- W2030611346 hasRelatedWork W2953083558 @default.
- W2030611346 hasRelatedWork W3005439739 @default.
- W2030611346 hasRelatedWork W3037770290 @default.
- W2030611346 hasRelatedWork W4205705013 @default.
- W2030611346 hasRelatedWork W4287869347 @default.
- W2030611346 hasRelatedWork W4300511536 @default.
- W2030611346 hasRelatedWork W4362599004 @default.
- W2030611346 isParatext "false" @default.
- W2030611346 isRetracted "false" @default.
- W2030611346 magId "2030611346" @default.
- W2030611346 workType "article" @default.