Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313266788> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4313266788 abstract "Nowadays, deep learning models enable numerous safety-critical applications, such as biometric authentication, medical diagnosis support, and self-driving cars. However, previous studies have frequently demonstrated that these models are attackable through slight modifications of their inputs, so-called adversarial attacks. Hence, researchers proposed investigating examples of these attacks with explainable artificial intelligence to understand them better. In this line, we developed an expert tool to explore adversarial attacks and defenses against them. To demonstrate the capabilities of our visualization tool, we worked with the publicly available CIFAR-10 dataset and generated one-pixel attacks. After that, we conducted an online evaluation with 16 experts. We found that our tool is usable and practical, providing evidence that it can support understanding, explaining, and preventing adversarial examples." @default.
- W4313266788 created "2023-01-06" @default.
- W4313266788 creator A5015767175 @default.
- W4313266788 creator A5020519967 @default.
- W4313266788 creator A5024328962 @default.
- W4313266788 creator A5025264966 @default.
- W4313266788 creator A5066229665 @default.
- W4313266788 date "2022-11-27" @default.
- W4313266788 modified "2023-09-28" @default.
- W4313266788 title "ExplAInable Pixels: Investigating One-Pixel Attacks on Deep Learning Models with Explainable Visualizations" @default.
- W4313266788 cites W1932198206 @default.
- W4313266788 cites W2156196376 @default.
- W4313266788 cites W2282821441 @default.
- W4313266788 cites W2342084405 @default.
- W4313266788 cites W2535873859 @default.
- W4313266788 cites W2611052251 @default.
- W4313266788 cites W2618043096 @default.
- W4313266788 cites W2954503794 @default.
- W4313266788 cites W2964082701 @default.
- W4313266788 cites W2981731882 @default.
- W4313266788 cites W2983371255 @default.
- W4313266788 cites W3008128620 @default.
- W4313266788 cites W3093223973 @default.
- W4313266788 cites W3100711616 @default.
- W4313266788 cites W3193088178 @default.
- W4313266788 doi "https://doi.org/10.1145/3568444.3568469" @default.
- W4313266788 hasPublicationYear "2022" @default.
- W4313266788 type Work @default.
- W4313266788 citedByCount "1" @default.
- W4313266788 countsByYear W43132667882023 @default.
- W4313266788 crossrefType "proceedings-article" @default.
- W4313266788 hasAuthorship W4313266788A5015767175 @default.
- W4313266788 hasAuthorship W4313266788A5020519967 @default.
- W4313266788 hasAuthorship W4313266788A5024328962 @default.
- W4313266788 hasAuthorship W4313266788A5025264966 @default.
- W4313266788 hasAuthorship W4313266788A5066229665 @default.
- W4313266788 hasConcept C108583219 @default.
- W4313266788 hasConcept C154945302 @default.
- W4313266788 hasConcept C160633673 @default.
- W4313266788 hasConcept C31972630 @default.
- W4313266788 hasConcept C36464697 @default.
- W4313266788 hasConcept C41008148 @default.
- W4313266788 hasConceptScore W4313266788C108583219 @default.
- W4313266788 hasConceptScore W4313266788C154945302 @default.
- W4313266788 hasConceptScore W4313266788C160633673 @default.
- W4313266788 hasConceptScore W4313266788C31972630 @default.
- W4313266788 hasConceptScore W4313266788C36464697 @default.
- W4313266788 hasConceptScore W4313266788C41008148 @default.
- W4313266788 hasLocation W43132667881 @default.
- W4313266788 hasOpenAccess W4313266788 @default.
- W4313266788 hasPrimaryLocation W43132667881 @default.
- W4313266788 hasRelatedWork W121273120 @default.
- W4313266788 hasRelatedWork W2002009170 @default.
- W4313266788 hasRelatedWork W2034462085 @default.
- W4313266788 hasRelatedWork W2090093270 @default.
- W4313266788 hasRelatedWork W2141888456 @default.
- W4313266788 hasRelatedWork W2337415362 @default.
- W4313266788 hasRelatedWork W2740820121 @default.
- W4313266788 hasRelatedWork W3005455252 @default.
- W4313266788 hasRelatedWork W317572212 @default.
- W4313266788 hasRelatedWork W4312857205 @default.
- W4313266788 isParatext "false" @default.
- W4313266788 isRetracted "false" @default.
- W4313266788 workType "article" @default.