Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204139034> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W3204139034 endingPage "9" @default.
- W3204139034 startingPage "1" @default.
- W3204139034 abstract "Nowadays, deep learning models play an important role in a variety of scenarios, such as image classification, natural language processing, and speech recognition. However, deep learning models are shown to be vulnerable; a small change to the original data may affect the output of the model, which may incur severe consequences such as misrecognition and privacy leakage. The intentionally modified data is referred to as adversarial examples. In this paper, we explore the security vulnerabilities of deep learning models designed for textual analysis. Specifically, we propose a visual similar word replacement (VSWR) algorithm to generate adversarial examples against textual analysis models. By using adversarial examples as the input of deep learning models, we verified that deep learning models are vulnerable to such adversarial attacks. We have conducted experiments on several sentiment analysis deep learning models to evaluate the performance. The results also confirmed that the generated adversarial examples could successfully attack deep learning models. As the number of modified words increases, the model prediction accuracy becomes lower. This kind of adversarial attack implies security vulnerabilities of deep learning models." @default.
- W3204139034 created "2021-10-11" @default.
- W3204139034 creator A5000591181 @default.
- W3204139034 creator A5033732336 @default.
- W3204139034 creator A5057867117 @default.
- W3204139034 creator A5070856186 @default.
- W3204139034 creator A5081140857 @default.
- W3204139034 date "2021-09-27" @default.
- W3204139034 modified "2023-10-16" @default.
- W3204139034 title "Exploring Security Vulnerabilities of Deep Learning Models by Adversarial Attacks" @default.
- W3204139034 cites W2180612164 @default.
- W3204139034 cites W2402268235 @default.
- W3204139034 cites W2799194071 @default.
- W3204139034 cites W2941002834 @default.
- W3204139034 cites W2962818281 @default.
- W3204139034 cites W3026797990 @default.
- W3204139034 cites W3034397670 @default.
- W3204139034 cites W3040265205 @default.
- W3204139034 cites W3081204102 @default.
- W3204139034 cites W3129307930 @default.
- W3204139034 cites W4288953700 @default.
- W3204139034 doi "https://doi.org/10.1155/2021/9969867" @default.
- W3204139034 hasPublicationYear "2021" @default.
- W3204139034 type Work @default.
- W3204139034 sameAs 3204139034 @default.
- W3204139034 citedByCount "1" @default.
- W3204139034 countsByYear W32041390342023 @default.
- W3204139034 crossrefType "journal-article" @default.
- W3204139034 hasAuthorship W3204139034A5000591181 @default.
- W3204139034 hasAuthorship W3204139034A5033732336 @default.
- W3204139034 hasAuthorship W3204139034A5057867117 @default.
- W3204139034 hasAuthorship W3204139034A5070856186 @default.
- W3204139034 hasAuthorship W3204139034A5081140857 @default.
- W3204139034 hasBestOaLocation W32041390341 @default.
- W3204139034 hasConcept C108583219 @default.
- W3204139034 hasConcept C119857082 @default.
- W3204139034 hasConcept C154945302 @default.
- W3204139034 hasConcept C204321447 @default.
- W3204139034 hasConcept C37736160 @default.
- W3204139034 hasConcept C41008148 @default.
- W3204139034 hasConceptScore W3204139034C108583219 @default.
- W3204139034 hasConceptScore W3204139034C119857082 @default.
- W3204139034 hasConceptScore W3204139034C154945302 @default.
- W3204139034 hasConceptScore W3204139034C204321447 @default.
- W3204139034 hasConceptScore W3204139034C37736160 @default.
- W3204139034 hasConceptScore W3204139034C41008148 @default.
- W3204139034 hasFunder F4320321001 @default.
- W3204139034 hasLocation W32041390341 @default.
- W3204139034 hasOpenAccess W3204139034 @default.
- W3204139034 hasPrimaryLocation W32041390341 @default.
- W3204139034 hasRelatedWork W2922457425 @default.
- W3204139034 hasRelatedWork W3014300295 @default.
- W3204139034 hasRelatedWork W3164822677 @default.
- W3204139034 hasRelatedWork W4223943233 @default.
- W3204139034 hasRelatedWork W4225161397 @default.
- W3204139034 hasRelatedWork W4250304930 @default.
- W3204139034 hasRelatedWork W4309045103 @default.
- W3204139034 hasRelatedWork W4312200629 @default.
- W3204139034 hasRelatedWork W4360585206 @default.
- W3204139034 hasRelatedWork W4364306694 @default.
- W3204139034 hasVolume "2021" @default.
- W3204139034 isParatext "false" @default.
- W3204139034 isRetracted "false" @default.
- W3204139034 magId "3204139034" @default.
- W3204139034 workType "article" @default.