Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313032622> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4313032622 endingPage "974" @default.
- W4313032622 startingPage "964" @default.
- W4313032622 abstract "Deep learning has shown impressive performance in numerous applications. However, recent studies have found that deep learning models are vulnerable to adversarial attacks, where the attacker adds imperceptible perturbations into benign samples to induce misclassifications. Adversarial attacks in the digital domain focus on constructing imperceptible perturbations. However, they are always less effective in the physical world because the perturbations may be destroyed when captured by the camera. Most physical adversarial attacks require adding invisible adversarial features (e.g., a sticker or a laser) to the target object, which may be noticed by human eyes. In this work, we propose to employ image transformation to generate more natural adversarial samples in the physical world. Concretely, we propose two attack algorithms to satisfy different attack goals: <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Efficient-AATR</i> employs a greedy strategy to generate adversarial samples with fewer queries; <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Effective-AATR</i> employs an adaptive particle swarm optimization algorithm to search for the most effective adversarial samples within the given the number of queries. Extensive experiments demonstrate the superiority of our attacks compared with state-of-the-art adversarial attacks under mainstream defenses." @default.
- W4313032622 created "2023-01-06" @default.
- W4313032622 creator A5024565956 @default.
- W4313032622 creator A5025130238 @default.
- W4313032622 creator A5046950426 @default.
- W4313032622 creator A5066542952 @default.
- W4313032622 creator A5070447777 @default.
- W4313032622 date "2023-06-01" @default.
- W4313032622 modified "2023-10-15" @default.
- W4313032622 title "Physical Black-Box Adversarial Attacks Through Transformations" @default.
- W4313032622 cites W1998324813 @default.
- W4313032622 cites W2001658805 @default.
- W4313032622 cites W2031342017 @default.
- W4313032622 cites W2084052726 @default.
- W4313032622 cites W2109364787 @default.
- W4313032622 cites W2124477890 @default.
- W4313032622 cites W2603766943 @default.
- W4313032622 cites W2788848944 @default.
- W4313032622 cites W2798302089 @default.
- W4313032622 cites W2947133760 @default.
- W4313032622 cites W2963540401 @default.
- W4313032622 cites W2972986629 @default.
- W4313032622 cites W2990183786 @default.
- W4313032622 cites W2998600476 @default.
- W4313032622 cites W3015625436 @default.
- W4313032622 cites W3035182590 @default.
- W4313032622 cites W3035467354 @default.
- W4313032622 cites W3041992316 @default.
- W4313032622 cites W3097573595 @default.
- W4313032622 cites W3105976275 @default.
- W4313032622 cites W3108058995 @default.
- W4313032622 cites W3167676691 @default.
- W4313032622 cites W3173859330 @default.
- W4313032622 cites W3174032462 @default.
- W4313032622 cites W3175451538 @default.
- W4313032622 cites W3188304288 @default.
- W4313032622 cites W3203961508 @default.
- W4313032622 cites W3210780202 @default.
- W4313032622 cites W4214502238 @default.
- W4313032622 cites W4214585697 @default.
- W4313032622 cites W4214870408 @default.
- W4313032622 cites W4224950673 @default.
- W4313032622 cites W4226058100 @default.
- W4313032622 cites W4313138527 @default.
- W4313032622 doi "https://doi.org/10.1109/tbdata.2022.3227318" @default.
- W4313032622 hasPublicationYear "2023" @default.
- W4313032622 type Work @default.
- W4313032622 citedByCount "0" @default.
- W4313032622 crossrefType "journal-article" @default.
- W4313032622 hasAuthorship W4313032622A5024565956 @default.
- W4313032622 hasAuthorship W4313032622A5025130238 @default.
- W4313032622 hasAuthorship W4313032622A5046950426 @default.
- W4313032622 hasAuthorship W4313032622A5066542952 @default.
- W4313032622 hasAuthorship W4313032622A5070447777 @default.
- W4313032622 hasConcept C108583219 @default.
- W4313032622 hasConcept C11413529 @default.
- W4313032622 hasConcept C115961682 @default.
- W4313032622 hasConcept C119857082 @default.
- W4313032622 hasConcept C134306372 @default.
- W4313032622 hasConcept C154945302 @default.
- W4313032622 hasConcept C33923547 @default.
- W4313032622 hasConcept C36503486 @default.
- W4313032622 hasConcept C37736160 @default.
- W4313032622 hasConcept C41008148 @default.
- W4313032622 hasConcept C80444323 @default.
- W4313032622 hasConceptScore W4313032622C108583219 @default.
- W4313032622 hasConceptScore W4313032622C11413529 @default.
- W4313032622 hasConceptScore W4313032622C115961682 @default.
- W4313032622 hasConceptScore W4313032622C119857082 @default.
- W4313032622 hasConceptScore W4313032622C134306372 @default.
- W4313032622 hasConceptScore W4313032622C154945302 @default.
- W4313032622 hasConceptScore W4313032622C33923547 @default.
- W4313032622 hasConceptScore W4313032622C36503486 @default.
- W4313032622 hasConceptScore W4313032622C37736160 @default.
- W4313032622 hasConceptScore W4313032622C41008148 @default.
- W4313032622 hasConceptScore W4313032622C80444323 @default.
- W4313032622 hasFunder F4320320751 @default.
- W4313032622 hasFunder F4320321001 @default.
- W4313032622 hasIssue "3" @default.
- W4313032622 hasLocation W43130326221 @default.
- W4313032622 hasOpenAccess W4313032622 @default.
- W4313032622 hasPrimaryLocation W43130326221 @default.
- W4313032622 hasRelatedWork W3014300295 @default.
- W4313032622 hasRelatedWork W3164822677 @default.
- W4313032622 hasRelatedWork W4223943233 @default.
- W4313032622 hasRelatedWork W4225161397 @default.
- W4313032622 hasRelatedWork W4250304930 @default.
- W4313032622 hasRelatedWork W4309045103 @default.
- W4313032622 hasRelatedWork W4312200629 @default.
- W4313032622 hasRelatedWork W4360585206 @default.
- W4313032622 hasRelatedWork W4364306694 @default.
- W4313032622 hasRelatedWork W4379255972 @default.
- W4313032622 hasVolume "9" @default.
- W4313032622 isParatext "false" @default.
- W4313032622 isRetracted "false" @default.
- W4313032622 workType "article" @default.