Matches in SemOpenAlex for { <https://semopenalex.org/work/W3024533331> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3024533331 abstract "As a primary form of communication, text is used widely for online communications, including e-mail conversations, mobile text messaging, chatroom and forum discussions. Modern systems include facilities such as predictive text, recently implemented using deep learning algorithms, to estimate the next word to be written based on previous historical entries. However, we often enter sensitive information such as passwords using the same input devices - namely, smartphone soft keyboards. In this paper, we explore the problem of deep learning models which memorise sensitive training data, and how secrets can be extracted from predictive text models. We propose a general black-box attack algorithm to accomplish this for all kinds of memorised sequences, discuss mitigations and countermeasures, and explore how this attack vector could be deployed on an Android or iOS mobile device platforms as part of target reconnaissance." @default.
- W3024533331 created "2020-05-21" @default.
- W3024533331 creator A5053235466 @default.
- W3024533331 creator A5060168830 @default.
- W3024533331 date "2020-06-01" @default.
- W3024533331 modified "2023-10-16" @default.
- W3024533331 title "“What did you say?”: Extracting unintentional secrets from predictive text learning systems" @default.
- W3024533331 cites W1995875735 @default.
- W3024533331 cites W2016043834 @default.
- W3024533331 cites W2051267297 @default.
- W3024533331 cites W2064675550 @default.
- W3024533331 cites W2109426455 @default.
- W3024533331 cites W2473418344 @default.
- W3024533331 cites W2512472178 @default.
- W3024533331 cites W2535690855 @default.
- W3024533331 cites W2795435272 @default.
- W3024533331 cites W2884943453 @default.
- W3024533331 cites W2895805829 @default.
- W3024533331 cites W2912094291 @default.
- W3024533331 cites W2930926105 @default.
- W3024533331 cites W2956998997 @default.
- W3024533331 cites W2963456518 @default.
- W3024533331 doi "https://doi.org/10.1109/cybersecurity49315.2020.9138882" @default.
- W3024533331 hasPublicationYear "2020" @default.
- W3024533331 type Work @default.
- W3024533331 sameAs 3024533331 @default.
- W3024533331 citedByCount "2" @default.
- W3024533331 countsByYear W30245333312023 @default.
- W3024533331 crossrefType "proceedings-article" @default.
- W3024533331 hasAuthorship W3024533331A5053235466 @default.
- W3024533331 hasAuthorship W3024533331A5060168830 @default.
- W3024533331 hasConcept C108583219 @default.
- W3024533331 hasConcept C109297577 @default.
- W3024533331 hasConcept C111919701 @default.
- W3024533331 hasConcept C119857082 @default.
- W3024533331 hasConcept C136764020 @default.
- W3024533331 hasConcept C154945302 @default.
- W3024533331 hasConcept C186967261 @default.
- W3024533331 hasConcept C204321447 @default.
- W3024533331 hasConcept C38652104 @default.
- W3024533331 hasConcept C41008148 @default.
- W3024533331 hasConcept C557433098 @default.
- W3024533331 hasConceptScore W3024533331C108583219 @default.
- W3024533331 hasConceptScore W3024533331C109297577 @default.
- W3024533331 hasConceptScore W3024533331C111919701 @default.
- W3024533331 hasConceptScore W3024533331C119857082 @default.
- W3024533331 hasConceptScore W3024533331C136764020 @default.
- W3024533331 hasConceptScore W3024533331C154945302 @default.
- W3024533331 hasConceptScore W3024533331C186967261 @default.
- W3024533331 hasConceptScore W3024533331C204321447 @default.
- W3024533331 hasConceptScore W3024533331C38652104 @default.
- W3024533331 hasConceptScore W3024533331C41008148 @default.
- W3024533331 hasConceptScore W3024533331C557433098 @default.
- W3024533331 hasLocation W30245333311 @default.
- W3024533331 hasOpenAccess W3024533331 @default.
- W3024533331 hasPrimaryLocation W30245333311 @default.
- W3024533331 hasRelatedWork W3014300295 @default.
- W3024533331 hasRelatedWork W3164822677 @default.
- W3024533331 hasRelatedWork W4223943233 @default.
- W3024533331 hasRelatedWork W4225161397 @default.
- W3024533331 hasRelatedWork W4250304930 @default.
- W3024533331 hasRelatedWork W4309045103 @default.
- W3024533331 hasRelatedWork W4312200629 @default.
- W3024533331 hasRelatedWork W4360585206 @default.
- W3024533331 hasRelatedWork W4364306694 @default.
- W3024533331 hasRelatedWork W4380086463 @default.
- W3024533331 isParatext "false" @default.
- W3024533331 isRetracted "false" @default.
- W3024533331 magId "3024533331" @default.
- W3024533331 workType "article" @default.