Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312658100> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4312658100 endingPage "757" @default.
- W4312658100 startingPage "744" @default.
- W4312658100 abstract "Much of the success of fingerprint recognition is attributed to minutiae-based fingerprint representation. It was believed that minutiae templates could not be inverted to obtain a high fidelity fingerprint image, but this assumption has been shown to be false. The success of deep learning has resulted in alternative fingerprint representations (embeddings), in the hope that they might offer better recognition accuracy as well as non-invertibility of deep network-based templates. We evaluate whether deep fingerprint templates suffer from the same reconstruction attacks as the minutiae templates. We show that while a deep template can be inverted to produce a fingerprint image that could be matched to its source image, deep templates are more resistant to reconstruction attacks than minutiae templates. In particular, reconstructed fingerprint images from minutiae templates yield a TAR of about 100.0% (98.3%) @ FAR of 0.01% for type-I (type-II) attacks using a state-of-the-art commercial fingerprint matcher, when tested on NIST SD4. The corresponding attack performance for reconstructed fingerprint images from deep templates using the same commercial matcher yields a TAR of less than 1% for both type-I and type-II attacks; however, when the reconstructed images are matched using the same deep network, they achieve a TAR of 85.95% (68.10%) for type-I (type-II) attacks. Furthermore, what is missing from previous fingerprint template inversion studies is an evaluation of the black-box attack performance, which we perform using 3 different state-of-the-art fingerprint matchers. We conclude that fingerprint images generated by inverting minutiae templates are highly susceptible to both white-box and black-box attack evaluations, while fingerprint images generated by deep templates are resistant to black-box evaluations and comparatively less susceptible to white-box evaluations." @default.
- W4312658100 created "2023-01-05" @default.
- W4312658100 creator A5002039083 @default.
- W4312658100 creator A5007029060 @default.
- W4312658100 creator A5027893701 @default.
- W4312658100 creator A5077233348 @default.
- W4312658100 date "2023-01-01" @default.
- W4312658100 modified "2023-10-14" @default.
- W4312658100 title "Fingerprint Template Invertibility: Minutiae vs. Deep Templates" @default.
- W4312658100 cites W1483712199 @default.
- W4312658100 cites W1951183756 @default.
- W4312658100 cites W2005399687 @default.
- W4312658100 cites W2014297961 @default.
- W4312658100 cites W2093929087 @default.
- W4312658100 cites W2118944716 @default.
- W4312658100 cites W2146112636 @default.
- W4312658100 cites W2194775991 @default.
- W4312658100 cites W2792557137 @default.
- W4312658100 cites W2798724621 @default.
- W4312658100 cites W2911297878 @default.
- W4312658100 cites W2963165122 @default.
- W4312658100 cites W2963812294 @default.
- W4312658100 cites W2975084324 @default.
- W4312658100 cites W2996883050 @default.
- W4312658100 cites W3118940050 @default.
- W4312658100 cites W3119896570 @default.
- W4312658100 cites W4230579564 @default.
- W4312658100 doi "https://doi.org/10.1109/tifs.2022.3229587" @default.
- W4312658100 hasPublicationYear "2023" @default.
- W4312658100 type Work @default.
- W4312658100 citedByCount "2" @default.
- W4312658100 countsByYear W43126581002023 @default.
- W4312658100 crossrefType "journal-article" @default.
- W4312658100 hasAuthorship W4312658100A5002039083 @default.
- W4312658100 hasAuthorship W4312658100A5007029060 @default.
- W4312658100 hasAuthorship W4312658100A5027893701 @default.
- W4312658100 hasAuthorship W4312658100A5077233348 @default.
- W4312658100 hasBestOaLocation W43126581002 @default.
- W4312658100 hasConcept C108583219 @default.
- W4312658100 hasConcept C153180895 @default.
- W4312658100 hasConcept C154945302 @default.
- W4312658100 hasConcept C168406668 @default.
- W4312658100 hasConcept C199360897 @default.
- W4312658100 hasConcept C2777826928 @default.
- W4312658100 hasConcept C31972630 @default.
- W4312658100 hasConcept C41008148 @default.
- W4312658100 hasConcept C67174900 @default.
- W4312658100 hasConcept C82714645 @default.
- W4312658100 hasConceptScore W4312658100C108583219 @default.
- W4312658100 hasConceptScore W4312658100C153180895 @default.
- W4312658100 hasConceptScore W4312658100C154945302 @default.
- W4312658100 hasConceptScore W4312658100C168406668 @default.
- W4312658100 hasConceptScore W4312658100C199360897 @default.
- W4312658100 hasConceptScore W4312658100C2777826928 @default.
- W4312658100 hasConceptScore W4312658100C31972630 @default.
- W4312658100 hasConceptScore W4312658100C41008148 @default.
- W4312658100 hasConceptScore W4312658100C67174900 @default.
- W4312658100 hasConceptScore W4312658100C82714645 @default.
- W4312658100 hasLocation W43126581001 @default.
- W4312658100 hasLocation W43126581002 @default.
- W4312658100 hasOpenAccess W4312658100 @default.
- W4312658100 hasPrimaryLocation W43126581001 @default.
- W4312658100 hasRelatedWork W1948266990 @default.
- W4312658100 hasRelatedWork W1995358885 @default.
- W4312658100 hasRelatedWork W2072387332 @default.
- W4312658100 hasRelatedWork W2075033769 @default.
- W4312658100 hasRelatedWork W2101068842 @default.
- W4312658100 hasRelatedWork W2124383217 @default.
- W4312658100 hasRelatedWork W2734991885 @default.
- W4312658100 hasRelatedWork W2903176029 @default.
- W4312658100 hasRelatedWork W2997969508 @default.
- W4312658100 hasRelatedWork W4293863368 @default.
- W4312658100 hasVolume "18" @default.
- W4312658100 isParatext "false" @default.
- W4312658100 isRetracted "false" @default.
- W4312658100 workType "article" @default.