Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969184416> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2969184416 endingPage "25" @default.
- W2969184416 startingPage "1" @default.
- W2969184416 abstract "In recent years, deep learning frameworks have been applied in many domains and achieved promising performance. However, recent work have demonstrated that deep learning frameworks are vulnerable to adversarial attacks. A trained neural network can be manipulated by small perturbations added to legitimate samples. In computer vision domain, these small perturbations could be imperceptible to human. As deep learning techniques have become the core part for many security-critical applications including identity recognition camera, malware detection software, self-driving cars, adversarial attacks have become one crucial security threat to many deep learning applications in real world. In this chapter, we first review some state-of-the-art adversarial attack techniques for deep learning frameworks in both white-box and black-box settings. We then discuss recent methods to defend against adversarial attacks on deep learning frameworks. Finally, we explore recent work applying adversarial attack techniques to some popular commercial deep learning applications, such as image classification, speech recognition and malware detection. These projects demonstrate that many commercial deep learning frameworks are vulnerable to malicious cyber security attacks." @default.
- W2969184416 created "2019-08-22" @default.
- W2969184416 creator A5000050561 @default.
- W2969184416 creator A5037947876 @default.
- W2969184416 creator A5071037763 @default.
- W2969184416 date "2019-01-01" @default.
- W2969184416 modified "2023-10-18" @default.
- W2969184416 title "Adversarial Attack, Defense, and Applications with Deep Learning Frameworks" @default.
- W2969184416 cites W1494198834 @default.
- W2969184416 cites W1965052658 @default.
- W2969184416 cites W2030611346 @default.
- W2969184416 cites W2097117768 @default.
- W2969184416 cites W2108598243 @default.
- W2969184416 cites W2112796928 @default.
- W2969184416 cites W2117539524 @default.
- W2969184416 cites W2122672392 @default.
- W2969184416 cites W2145901875 @default.
- W2969184416 cites W2155893237 @default.
- W2969184416 cites W2180612164 @default.
- W2969184416 cites W2183341477 @default.
- W2969184416 cites W2243397390 @default.
- W2969184416 cites W2603766943 @default.
- W2969184416 cites W2783155279 @default.
- W2969184416 cites W2919115771 @default.
- W2969184416 doi "https://doi.org/10.1007/978-3-030-13057-2_1" @default.
- W2969184416 hasPublicationYear "2019" @default.
- W2969184416 type Work @default.
- W2969184416 sameAs 2969184416 @default.
- W2969184416 citedByCount "4" @default.
- W2969184416 countsByYear W29691844162020 @default.
- W2969184416 countsByYear W29691844162021 @default.
- W2969184416 countsByYear W29691844162023 @default.
- W2969184416 crossrefType "book-chapter" @default.
- W2969184416 hasAuthorship W2969184416A5000050561 @default.
- W2969184416 hasAuthorship W2969184416A5037947876 @default.
- W2969184416 hasAuthorship W2969184416A5071037763 @default.
- W2969184416 hasConcept C108583219 @default.
- W2969184416 hasConcept C119857082 @default.
- W2969184416 hasConcept C134306372 @default.
- W2969184416 hasConcept C154945302 @default.
- W2969184416 hasConcept C2522767166 @default.
- W2969184416 hasConcept C2984842247 @default.
- W2969184416 hasConcept C33923547 @default.
- W2969184416 hasConcept C36503486 @default.
- W2969184416 hasConcept C37736160 @default.
- W2969184416 hasConcept C38652104 @default.
- W2969184416 hasConcept C41008148 @default.
- W2969184416 hasConcept C541664917 @default.
- W2969184416 hasConcept C94966114 @default.
- W2969184416 hasConceptScore W2969184416C108583219 @default.
- W2969184416 hasConceptScore W2969184416C119857082 @default.
- W2969184416 hasConceptScore W2969184416C134306372 @default.
- W2969184416 hasConceptScore W2969184416C154945302 @default.
- W2969184416 hasConceptScore W2969184416C2522767166 @default.
- W2969184416 hasConceptScore W2969184416C2984842247 @default.
- W2969184416 hasConceptScore W2969184416C33923547 @default.
- W2969184416 hasConceptScore W2969184416C36503486 @default.
- W2969184416 hasConceptScore W2969184416C37736160 @default.
- W2969184416 hasConceptScore W2969184416C38652104 @default.
- W2969184416 hasConceptScore W2969184416C41008148 @default.
- W2969184416 hasConceptScore W2969184416C541664917 @default.
- W2969184416 hasConceptScore W2969184416C94966114 @default.
- W2969184416 hasLocation W29691844161 @default.
- W2969184416 hasOpenAccess W2969184416 @default.
- W2969184416 hasPrimaryLocation W29691844161 @default.
- W2969184416 hasRelatedWork W2272495070 @default.
- W2969184416 hasRelatedWork W2952919291 @default.
- W2969184416 hasRelatedWork W2968586400 @default.
- W2969184416 hasRelatedWork W3120979750 @default.
- W2969184416 hasRelatedWork W3193857078 @default.
- W2969184416 hasRelatedWork W4213432687 @default.
- W2969184416 hasRelatedWork W4225493432 @default.
- W2969184416 hasRelatedWork W4293054861 @default.
- W2969184416 hasRelatedWork W4300837091 @default.
- W2969184416 hasRelatedWork W4316087074 @default.
- W2969184416 isParatext "false" @default.
- W2969184416 isRetracted "false" @default.
- W2969184416 magId "2969184416" @default.
- W2969184416 workType "book-chapter" @default.