Worst-Case Morphs using Wasserstein ALI and Improved MIPGAN
A morph is a combination of two separate facial images and contains identity information of two different people. When used in an identity document, both people can be authenticated by a biometric Face Recognition (FR) system. Morphs can be generated using either a landmark-based approach or approac...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , |
Format | Paper Journal Article |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
13.10.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | A morph is a combination of two separate facial images and contains identity information of two different people. When used in an identity document, both people can be authenticated by a biometric Face Recognition (FR) system. Morphs can be generated using either a landmark-based approach or approaches based on deep learning such as Generative Adversarial Networks (GAN). In a recent paper, we introduced a \emph{worst-case} upper bound on how challenging morphing attacks can be for an FR system. The closer morphs are to this upper bound, the bigger the challenge they pose to FR. We introduced an approach with which it was possible to generate morphs that approximate this upper bound for a known FR system (white box), but not for unknown (black box) FR systems. In this paper, we introduce a morph generation method that can approximate worst-case morphs even when the FR system is not known. A key contribution is that we include the goal of generating difficult morphs \emph{during} training. Our method is based on Adversarially Learned Inference (ALI) and uses concepts from Wasserstein GANs trained with Gradient Penalty, which were introduced to stabilise the training of GANs. We include these concepts to achieve similar improvement in training stability and call the resulting method Wasserstein ALI (WALI). We finetune WALI using loss functions designed specifically to improve the ability to manipulate identity information in facial images and show how it can generate morphs that are more challenging for FR systems than landmark- or GAN-based morphs. We also show how our findings can be used to improve MIPGAN, an existing StyleGAN-based morph generator. |
---|---|
AbstractList | A morph is a combination of two separate facial images and contains identity
information of two different people. When used in an identity document, both
people can be authenticated by a biometric Face Recognition (FR) system. Morphs
can be generated using either a landmark-based approach or approaches based on
deep learning such as Generative Adversarial Networks (GAN). In a recent paper,
we introduced a \emph{worst-case} upper bound on how challenging morphing
attacks can be for an FR system. The closer morphs are to this upper bound, the
bigger the challenge they pose to FR. We introduced an approach with which it
was possible to generate morphs that approximate this upper bound for a known
FR system (white box), but not for unknown (black box) FR systems.
In this paper, we introduce a morph generation method that can approximate
worst-case morphs even when the FR system is not known. A key contribution is
that we include the goal of generating difficult morphs \emph{during} training.
Our method is based on Adversarially Learned Inference (ALI) and uses concepts
from Wasserstein GANs trained with Gradient Penalty, which were introduced to
stabilise the training of GANs. We include these concepts to achieve similar
improvement in training stability and call the resulting method Wasserstein ALI
(WALI). We finetune WALI using loss functions designed specifically to improve
the ability to manipulate identity information in facial images and show how it
can generate morphs that are more challenging for FR systems than landmark- or
GAN-based morphs. We also show how our findings can be used to improve MIPGAN,
an existing StyleGAN-based morph generator. A morph is a combination of two separate facial images and contains identity information of two different people. When used in an identity document, both people can be authenticated by a biometric Face Recognition (FR) system. Morphs can be generated using either a landmark-based approach or approaches based on deep learning such as Generative Adversarial Networks (GAN). In a recent paper, we introduced a \emph{worst-case} upper bound on how challenging morphing attacks can be for an FR system. The closer morphs are to this upper bound, the bigger the challenge they pose to FR. We introduced an approach with which it was possible to generate morphs that approximate this upper bound for a known FR system (white box), but not for unknown (black box) FR systems. In this paper, we introduce a morph generation method that can approximate worst-case morphs even when the FR system is not known. A key contribution is that we include the goal of generating difficult morphs \emph{during} training. Our method is based on Adversarially Learned Inference (ALI) and uses concepts from Wasserstein GANs trained with Gradient Penalty, which were introduced to stabilise the training of GANs. We include these concepts to achieve similar improvement in training stability and call the resulting method Wasserstein ALI (WALI). We finetune WALI using loss functions designed specifically to improve the ability to manipulate identity information in facial images and show how it can generate morphs that are more challenging for FR systems than landmark- or GAN-based morphs. We also show how our findings can be used to improve MIPGAN, an existing StyleGAN-based morph generator. |
Author | Spreeuwers, Luuk J Nauta, Meike Liu, Lu Kelly, Una M Veldhuis, Raymond N J |
Author_xml | – sequence: 1 givenname: Una surname: Kelly middlename: M fullname: Kelly, Una M – sequence: 2 givenname: Meike surname: Nauta fullname: Nauta, Meike – sequence: 3 givenname: Lu surname: Liu fullname: Liu, Lu – sequence: 4 givenname: Luuk surname: Spreeuwers middlename: J fullname: Spreeuwers, Luuk J – sequence: 5 givenname: Raymond surname: Veldhuis middlename: N J fullname: Veldhuis, Raymond N J |
BackLink | https://doi.org/10.1155/1970/9353816$$DView published paper (Access to full text may be restricted) https://doi.org/10.48550/arXiv.2310.08371$$DView paper in arXiv |
BookMark | eNotj01Lw0AYhBdRsNb-AE8ueE7dfTf7hacQbA2k6qHQY3hjNppik7jbFP33xtbTwMwwzHNFztuudYTccDaPjZTsHv13c5iDGA1mhOZnZAJC8MjEAJdkFsKWMQZKg5RiQh42nQ_7KMXg6Krz_UegQ2jad7rBENwYuaalSZ5RbCua7XrfHVxFV9nrMnm-Jhc1fgY3-9cpWS8e1-lTlL8sszTJI7SSRzrGyilbaYWglEWEsuQoQEm0qEuuOaLVUtYxM7V9066soYRKlSAs00qJKbk9zR7Jit43O_Q_xR9hcSQcG3enxnjva3BhX2y7wbfjpwKMVloJAUb8AhRxU1I |
ContentType | Paper Journal Article |
Copyright | 2023. This work is published under http://creativecommons.org/licenses/by-nc-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. http://creativecommons.org/licenses/by-nc-sa/4.0 |
Copyright_xml | – notice: 2023. This work is published under http://creativecommons.org/licenses/by-nc-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: http://creativecommons.org/licenses/by-nc-sa/4.0 |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS AKY GOX |
DOI | 10.48550/arxiv.2310.08371 |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection arXiv Computer Science arXiv.org |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository – sequence: 2 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
ExternalDocumentID | 2310_08371 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS AKY GOX |
ID | FETCH-LOGICAL-a951-74ade69d76a2669aa2bb1a3265a9a7b171aa9755f408f9c7ebf2b2d6b23907663 |
IEDL.DBID | GOX |
IngestDate | Mon Jan 08 05:44:36 EST 2024 Thu Oct 10 16:53:29 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-a951-74ade69d76a2669aa2bb1a3265a9a7b171aa9755f408f9c7ebf2b2d6b23907663 |
OpenAccessLink | https://arxiv.org/abs/2310.08371 |
PQID | 2876763328 |
PQPubID | 2050157 |
ParticipantIDs | arxiv_primary_2310_08371 proquest_journals_2876763328 |
PublicationCentury | 2000 |
PublicationDate | 20231013 |
PublicationDateYYYYMMDD | 2023-10-13 |
PublicationDate_xml | – month: 10 year: 2023 text: 20231013 day: 13 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2023 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 1.9028751 |
SecondaryResourceType | preprint |
Snippet | A morph is a combination of two separate facial images and contains identity information of two different people. When used in an identity document, both... A morph is a combination of two separate facial images and contains identity information of two different people. When used in an identity document, both... |
SourceID | arxiv proquest |
SourceType | Open Access Repository Aggregation Database |
SubjectTerms | Coders Computer Science - Computer Vision and Pattern Recognition Generative adversarial networks Image reconstruction Training |
SummonAdditionalLinks | – databaseName: ProQuest Technology Collection dbid: 8FG link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV07T8MwELagFRIbTxUoyANrWuI8HIsBVRV9IFp1KGq36C52EEtSmoL4-ZzdFAYk1njKZ_vuu_PdfYzdBnT_BUaZF2VCU4CCwkOFyhPKz0GDVtLY3uHJNB69hE_LaFkn3Kq6rHJnE52h1mVmc-RdYvYx3YVAJA-rd8-qRtnX1VpCY581fTsJz3aKD4Y_ORYRS2LMwfYx043u6sL66-2zY0lNh8iHbZxvuk9_TLHzL4Mj1pzByqyP2Z4pTtiBK8vMqlN2vyiJnXl9cjV8UhIkFbeF6q98Aa5N0kpV8t7zmEOh-TY_YDSfjGfD3vSMzQeP8_7Iq-UOPLBa9zIEbWKlZQzkNBWAQPSB2FUECiT60gdQMory8C7JVSYN5gKFjlEEFOAScThnjaIsTItxFBTEJIEmdqPDUGUKcykBkCBI_CjDC9ZyP52uthMtUotH6vC4YO0dDml9mqv0F_vL_5ev2KGVY7e23Q_arLFZf5hrctobvHE78w1nGZUN priority: 102 providerName: ProQuest |
Title | Worst-Case Morphs using Wasserstein ALI and Improved MIPGAN |
URI | https://www.proquest.com/docview/2876763328 https://arxiv.org/abs/2310.08371 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV07T8MwED61ZWFBIEAtlMoDa4A4D8diKlVfiJQKFbVbdBcniKWt2oKY-O2ck1QMiMWDdR58tu--T74HwLXH719SkDpBKg0TFJIOadKO1G6OBo1Wmc0djifh6NV_XASLGoh9Lgxuvt4_y_rAtL214OOGQYJNEq9LaUO2hs-L8nOyKMVVyf_KMcYspv6Y1sJfDI7hqAJ6oluezAnUsuUp3M9XjLacHrsOEa94i1thA8_fxByLtEfbelJ0n8aC-b0o-X5mRDyeDruTM5gN-rPeyKnaFzhoe9crH00WaqNCZCeoESWRi4yWAtSoyFUuolZBkPt3Ua5TlVEuSZqQpMeElYHAOTSWq2XWBEGSSUnkGUYrxvd1qilXCpFYBZEbpNSCZrHpZF1WqEisPpJCHy1o7_WQVLdzmzBLCtmueDK6-H_lJRza1urWTrteGxq7zUd2xQ54Rx2oR4NhBw4e-pPpS6c4Ex7j7_4PE9uH_g |
link.rule.ids | 228,230,786,790,891,12792,21416,27956,33406,33777,43633,43838 |
linkProvider | Cornell University |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV09T8MwELWgEYKNT7VQwANrWuJ8OBYDKhWlhSaqUFG7Rec4QSxJaQri53N2UxiQWOMpz_bdu_PdPUKuXLz_TPqp7adMYYAimS2FFDYTTg4KlOCZ7h2O4mD44j3O_XmdcKvqssqNTTSGWpWpzpF3kdkHeBdcFt4u3m2tGqVfV2sJjW1i6ZGbYYNYd_fx5Pkny8ICjpzZXT9nmuFdXVh-vX12NK3pIP3QrfOW-fTHGBsPM9gn1gQW2fKAbGXFIdkxhZlpdURuZiXyM7uPzoZGJYJSUV2q_kpnYBoltVgl7Y1HFApF1xmCTNFoNHnoxcdkOrif9od2LXhgg1a75x6oLBCKB4BuUwAwKR1AfuWDAC4d7gAI7vu5dx3mIuWZzJlkKpDMxRAXqcMJaRRlkTUJlQzDmNBVyG-U54lUyJxzAIkQhI6fyhZpmp9OFuuZFonGIzF4tEh7g0NSn-cq-UX_9P_lS7I7nEbjZDyKn87InhZn15becduksVp-ZOfowlfyot6nbzZ3mWQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Worst-Case+Morphs+using+Wasserstein+ALI+and+Improved+MIPGAN&rft.jtitle=arXiv.org&rft.au=Kelly%2C+Una+M&rft.au=Nauta%2C+Meike&rft.au=Liu%2C+Lu&rft.au=Spreeuwers%2C+Luuk+J&rft.date=2023-10-13&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.2310.08371 |