Matches in SemOpenAlex for { <https://semopenalex.org/work/W3008533131> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3008533131 abstract "Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately designed small perturbations are added to the benign input samples to fool the deep learning model and degrade its performance. This paper considers transferability-based black-box attacks, where the attacker trains a substitute model to approximate the target model, and then generates adversarial examples from the substitute model to attack the target model. Learning a good substitute model is critical to the success of these attacks, but it requires a large number of queries to the target model. We propose a novel framework which uses query synthesis based active learning to improve the query efficiency i n t raining the substitute model. Experiments on three convolutional neural network (CNN) classifiers and three EEG datasets demonstrated that our method can improve the attack success rate with the same number of queries, or, in other words, our method requires fewer queries to achieve a desired attack performance. To our knowledge, this is the first work that integrates active learning and adversarial attacks for EEG-based BCIs." @default.
- W3008533131 created "2020-03-06" @default.
- W3008533131 creator A5008740867 @default.
- W3008533131 creator A5026121963 @default.
- W3008533131 creator A5081493613 @default.
- W3008533131 date "2019-12-01" @default.
- W3008533131 modified "2023-10-05" @default.
- W3008533131 title "Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces" @default.
- W3008533131 cites W2010005543 @default.
- W3008533131 cites W2024938223 @default.
- W3008533131 cites W2094017272 @default.
- W3008533131 cites W2098100592 @default.
- W3008533131 cites W2114804859 @default.
- W3008533131 cites W2119163516 @default.
- W3008533131 cites W2128909182 @default.
- W3008533131 cites W2130847623 @default.
- W3008533131 cites W2140413964 @default.
- W3008533131 cites W2169296125 @default.
- W3008533131 cites W2171671120 @default.
- W3008533131 cites W2243397390 @default.
- W3008533131 cites W2314733761 @default.
- W3008533131 cites W2535873859 @default.
- W3008533131 cites W2557301950 @default.
- W3008533131 cites W2603766943 @default.
- W3008533131 cites W2741907166 @default.
- W3008533131 cites W2895097814 @default.
- W3008533131 cites W2909905004 @default.
- W3008533131 cites W2930980596 @default.
- W3008533131 cites W2962755824 @default.
- W3008533131 cites W2963118571 @default.
- W3008533131 cites W2963595743 @default.
- W3008533131 cites W2963857521 @default.
- W3008533131 cites W2964117520 @default.
- W3008533131 cites W2964301649 @default.
- W3008533131 cites W3098943317 @default.
- W3008533131 cites W3102455230 @default.
- W3008533131 cites W4252861488 @default.
- W3008533131 doi "https://doi.org/10.1109/ssci44817.2019.9002719" @default.
- W3008533131 hasPublicationYear "2019" @default.
- W3008533131 type Work @default.
- W3008533131 sameAs 3008533131 @default.
- W3008533131 citedByCount "9" @default.
- W3008533131 countsByYear W30085331312019 @default.
- W3008533131 countsByYear W30085331312021 @default.
- W3008533131 countsByYear W30085331312022 @default.
- W3008533131 countsByYear W30085331312023 @default.
- W3008533131 crossrefType "proceedings-article" @default.
- W3008533131 hasAuthorship W3008533131A5008740867 @default.
- W3008533131 hasAuthorship W3008533131A5026121963 @default.
- W3008533131 hasAuthorship W3008533131A5081493613 @default.
- W3008533131 hasBestOaLocation W30085331312 @default.
- W3008533131 hasConcept C108583219 @default.
- W3008533131 hasConcept C118552586 @default.
- W3008533131 hasConcept C119857082 @default.
- W3008533131 hasConcept C140331021 @default.
- W3008533131 hasConcept C154945302 @default.
- W3008533131 hasConcept C15744967 @default.
- W3008533131 hasConcept C37736160 @default.
- W3008533131 hasConcept C41008148 @default.
- W3008533131 hasConcept C522805319 @default.
- W3008533131 hasConcept C61272859 @default.
- W3008533131 hasConcept C81363708 @default.
- W3008533131 hasConcept C94966114 @default.
- W3008533131 hasConceptScore W3008533131C108583219 @default.
- W3008533131 hasConceptScore W3008533131C118552586 @default.
- W3008533131 hasConceptScore W3008533131C119857082 @default.
- W3008533131 hasConceptScore W3008533131C140331021 @default.
- W3008533131 hasConceptScore W3008533131C154945302 @default.
- W3008533131 hasConceptScore W3008533131C15744967 @default.
- W3008533131 hasConceptScore W3008533131C37736160 @default.
- W3008533131 hasConceptScore W3008533131C41008148 @default.
- W3008533131 hasConceptScore W3008533131C522805319 @default.
- W3008533131 hasConceptScore W3008533131C61272859 @default.
- W3008533131 hasConceptScore W3008533131C81363708 @default.
- W3008533131 hasConceptScore W3008533131C94966114 @default.
- W3008533131 hasLocation W30085331311 @default.
- W3008533131 hasLocation W30085331312 @default.
- W3008533131 hasOpenAccess W3008533131 @default.
- W3008533131 hasPrimaryLocation W30085331311 @default.
- W3008533131 hasRelatedWork W2731899572 @default.
- W3008533131 hasRelatedWork W2914158293 @default.
- W3008533131 hasRelatedWork W2963115223 @default.
- W3008533131 hasRelatedWork W3121799932 @default.
- W3008533131 hasRelatedWork W3133861977 @default.
- W3008533131 hasRelatedWork W4200173597 @default.
- W3008533131 hasRelatedWork W4213093132 @default.
- W3008533131 hasRelatedWork W4287368650 @default.
- W3008533131 hasRelatedWork W4312417841 @default.
- W3008533131 hasRelatedWork W4321369474 @default.
- W3008533131 isParatext "false" @default.
- W3008533131 isRetracted "false" @default.
- W3008533131 magId "3008533131" @default.
- W3008533131 workType "article" @default.