FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281562364> ?p ?o ?g. }

• W4281562364 endingPage "1002" @default.
• W4281562364 startingPage "989" @default.
• W4281562364 abstract "The emergence of adversarial examples has aroused widespread attention to the safety of deep learning. Most recent research focuses on how to obtain adversarial examples which make networks’ predictions wrong, and rarely observe the changes in feature embedding space from the perspective of interpretability. In addition, researchers have proposed various attack algorithms for a single task, but there are few general methods that can perform multiple tasks at the same time, such as image classification, object detection, and face recognition. To resolve these issues, we propose a new attack algorithm CAMA for deep neural networks (DNNs). CAMA perturbs each feature extraction layer through adaptive feature measurement function, thereby disrupting the predicted class activation mapping of DNNs. Experiments show that CAMA is good at creating white-box adversarial examples on classification networks and has the highest attack success rate. To solve the problem of the disappearance of aggression caused by image transformation, we propose spread-spectrum compression CAMA, which achieve a better attack success rate under various defensive measures. In addition, we successfully attack face recognition networks and object detection networks using CAMA, and achieve excellent performance. It verifies that our algorithm is a general attack algorithm for attacking different tasks." @default.
• W4281562364 created "2022-05-27" @default.
• W4281562364 creator A5031567446 @default.
• W4281562364 creator A5035560190 @default.
• W4281562364 creator A5057916222 @default.
• W4281562364 creator A5060514022 @default.
• W4281562364 creator A5077536212 @default.
• W4281562364 date "2022-08-01" @default.
• W4281562364 modified "2023-09-26" @default.
• W4281562364 title "CAMA: Class activation mapping disruptive attack for deep neural networks" @default.
• W4281562364 cites W2031489346 @default.
• W4281562364 cites W2117539524 @default.
• W4281562364 cites W2325939864 @default.
• W4281562364 cites W2603766943 @default.
• W4281562364 cites W2618530766 @default.
• W4281562364 cites W2781800156 @default.
• W4281562364 cites W2891828758 @default.
• W4281562364 cites W2919115771 @default.
• W4281562364 cites W2929078203 @default.
• W4281562364 cites W2963428752 @default.
• W4281562364 cites W2963460857 @default.
• W4281562364 cites W2963976704 @default.
• W4281562364 cites W2965198951 @default.
• W4281562364 cites W2971649887 @default.
• W4281562364 cites W2993546896 @default.
• W4281562364 cites W3001083904 @default.
• W4281562364 cites W3016889634 @default.
• W4281562364 cites W3034455297 @default.
• W4281562364 cites W3103557498 @default.
• W4281562364 doi "https://doi.org/10.1016/j.neucom.2022.05.065" @default.
• W4281562364 hasPublicationYear "2022" @default.
• W4281562364 type Work @default.
• W4281562364 citedByCount "1" @default.
• W4281562364 countsByYear W42815623642022 @default.
• W4281562364 crossrefType "journal-article" @default.
• W4281562364 hasAuthorship W4281562364A5031567446 @default.
• W4281562364 hasAuthorship W4281562364A5035560190 @default.
• W4281562364 hasAuthorship W4281562364A5057916222 @default.
• W4281562364 hasAuthorship W4281562364A5060514022 @default.
• W4281562364 hasAuthorship W4281562364A5077536212 @default.
• W4281562364 hasConcept C108583219 @default.
• W4281562364 hasConcept C119857082 @default.
• W4281562364 hasConcept C138885662 @default.
• W4281562364 hasConcept C14036430 @default.
• W4281562364 hasConcept C144024400 @default.
• W4281562364 hasConcept C153180895 @default.
• W4281562364 hasConcept C154945302 @default.
• W4281562364 hasConcept C162324750 @default.
• W4281562364 hasConcept C187736073 @default.
• W4281562364 hasConcept C2776401178 @default.
• W4281562364 hasConcept C2777212361 @default.
• W4281562364 hasConcept C2779304628 @default.
• W4281562364 hasConcept C2780451532 @default.
• W4281562364 hasConcept C2781067378 @default.
• W4281562364 hasConcept C2781238097 @default.
• W4281562364 hasConcept C2984842247 @default.
• W4281562364 hasConcept C36289849 @default.
• W4281562364 hasConcept C37736160 @default.
• W4281562364 hasConcept C41008148 @default.
• W4281562364 hasConcept C41608201 @default.
• W4281562364 hasConcept C41895202 @default.
• W4281562364 hasConcept C50644808 @default.
• W4281562364 hasConcept C78458016 @default.
• W4281562364 hasConcept C86803240 @default.
• W4281562364 hasConceptScore W4281562364C108583219 @default.
• W4281562364 hasConceptScore W4281562364C119857082 @default.
• W4281562364 hasConceptScore W4281562364C138885662 @default.
• W4281562364 hasConceptScore W4281562364C14036430 @default.
• W4281562364 hasConceptScore W4281562364C144024400 @default.
• W4281562364 hasConceptScore W4281562364C153180895 @default.
• W4281562364 hasConceptScore W4281562364C154945302 @default.
• W4281562364 hasConceptScore W4281562364C162324750 @default.
• W4281562364 hasConceptScore W4281562364C187736073 @default.
• W4281562364 hasConceptScore W4281562364C2776401178 @default.
• W4281562364 hasConceptScore W4281562364C2777212361 @default.
• W4281562364 hasConceptScore W4281562364C2779304628 @default.
• W4281562364 hasConceptScore W4281562364C2780451532 @default.
• W4281562364 hasConceptScore W4281562364C2781067378 @default.
• W4281562364 hasConceptScore W4281562364C2781238097 @default.
• W4281562364 hasConceptScore W4281562364C2984842247 @default.
• W4281562364 hasConceptScore W4281562364C36289849 @default.
• W4281562364 hasConceptScore W4281562364C37736160 @default.
• W4281562364 hasConceptScore W4281562364C41008148 @default.
• W4281562364 hasConceptScore W4281562364C41608201 @default.
• W4281562364 hasConceptScore W4281562364C41895202 @default.
• W4281562364 hasConceptScore W4281562364C50644808 @default.
• W4281562364 hasConceptScore W4281562364C78458016 @default.
• W4281562364 hasConceptScore W4281562364C86803240 @default.
• W4281562364 hasFunder F4320306076 @default.
• W4281562364 hasFunder F4320306101 @default.
• W4281562364 hasFunder F4320321001 @default.
• W4281562364 hasFunder F4320324173 @default.
• W4281562364 hasFunder F4320330485 @default.
• W4281562364 hasFunder F4320338281 @default.
• W4281562364 hasFunder F4320338294 @default.
• W4281562364 hasLocation W42815623641 @default.
• W4281562364 hasOpenAccess W4281562364 @default.
• W4281562364 hasPrimaryLocation W42815623641 @default.

• next