Adversarial Attacks on Medical Segmentation Model via Transformation of Feature Statistics

Deep learning-based segmentation models have made a profound impact on medical procedures, with U-Net based computed tomography (CT) segmentation models exhibiting remarkable performance. Yet, even with these advances, these models are found to be vulnerable to adversarial attacks, a problem that eq...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Applied sciences Jg. 14; H. 6; S. 2576
Hauptverfasser:	Lee, Woonghee, Ju, Mingeon, Sim, Yura, Jung, Young Kul, Kim, Tae Hyung, Kim, Younghoon
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 01.03.2024
Schlagworte:	adversarial attacks computed tomography (CT) segmentation CT imaging data augmentation Deep learning deep learning-based segmentation Medical research Medical screening Methods realistic adversarial samples Standard deviation Statistics Tomography Germany
ISSN:	2076-3417, 2076-3417
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Deep learning-based segmentation models have made a profound impact on medical procedures, with U-Net based computed tomography (CT) segmentation models exhibiting remarkable performance. Yet, even with these advances, these models are found to be vulnerable to adversarial attacks, a problem that equally affects automatic CT segmentation models. Conventional adversarial attacks typically rely on adding noise or perturbations, leading to a compromise between the success rate of the attack and its perceptibility. In this study, we challenge this paradigm and introduce a novel generation of adversarial attacks aimed at deceiving both the target segmentation model and medical practitioners. Our approach aims to deceive a target model by altering the texture statistics of an organ while retaining its shape. We employ a real-time style transfer method, known as the texture reformer, which uses adaptive instance normalization (AdaIN) to change the statistics of an image’s feature.To induce transformation, we modify the AdaIN, which typically aligns the source and target image statistics. Through rigorous experiments, we demonstrate the effectiveness of our approach. Our adversarial samples successfully pass as realistic in blind tests conducted with physicians, surpassing the effectiveness of contemporary techniques. This innovative methodology not only offers a robust tool for benchmarking and validating automated CT segmentation systems but also serves as a potent mechanism for data augmentation, thereby enhancing model generalization. This dual capability significantly bolsters advancements in the field of deep learning-based medical and healthcare segmentation models.
AbstractList	Deep learning-based segmentation models have made a profound impact on medical procedures, with U-Net based computed tomography (CT) segmentation models exhibiting remarkable performance. Yet, even with these advances, these models are found to be vulnerable to adversarial attacks, a problem that equally affects automatic CT segmentation models. Conventional adversarial attacks typically rely on adding noise or perturbations, leading to a compromise between the success rate of the attack and its perceptibility. In this study, we challenge this paradigm and introduce a novel generation of adversarial attacks aimed at deceiving both the target segmentation model and medical practitioners. Our approach aims to deceive a target model by altering the texture statistics of an organ while retaining its shape. We employ a real-time style transfer method, known as the texture reformer, which uses adaptive instance normalization (AdaIN) to change the statistics of an image’s feature.To induce transformation, we modify the AdaIN, which typically aligns the source and target image statistics. Through rigorous experiments, we demonstrate the effectiveness of our approach. Our adversarial samples successfully pass as realistic in blind tests conducted with physicians, surpassing the effectiveness of contemporary techniques. This innovative methodology not only offers a robust tool for benchmarking and validating automated CT segmentation systems but also serves as a potent mechanism for data augmentation, thereby enhancing model generalization. This dual capability significantly bolsters advancements in the field of deep learning-based medical and healthcare segmentation models.
Audience	Academic
Author	Ju, Mingeon Jung, Young Kul Sim, Yura Kim, Younghoon Kim, Tae Hyung Lee, Woonghee
Author_xml	– sequence: 1 givenname: Woonghee orcidid: 0000-0001-7850-9913 surname: Lee fullname: Lee, Woonghee – sequence: 2 givenname: Mingeon orcidid: 0009-0004-5453-3731 surname: Ju fullname: Ju, Mingeon – sequence: 3 givenname: Yura surname: Sim fullname: Sim, Yura – sequence: 4 givenname: Young Kul orcidid: 0000-0002-6566-1382 surname: Jung fullname: Jung, Young Kul – sequence: 5 givenname: Tae Hyung orcidid: 0000-0002-7747-4293 surname: Kim fullname: Kim, Tae Hyung – sequence: 6 givenname: Younghoon orcidid: 0000-0002-3049-035X surname: Kim fullname: Kim, Younghoon
BookMark	eNptUctqHDEQHIIDcRyf_AMDOYa19Vo9jouJH-CQg52LL6JXai3azIw2ktaQv482ExMnWH1QU11VNF3vu6MpTdh1Z5Scc27IBex2VBDJlkq-6Y4ZUXLBBVVHL_p33WkpW9KeoVxTctw9rvwT5gI5wtCvagX3vfRp6r-gj65B97gZcapQ4wFMHof-KUL_kGEqIeVxHqTQXyHUfcb-_sAtNbryoXsbYCh4-uc_6b5dfX64vFncfb2-vVzdLZwwqi7WVFHB0YhApV8GhcITBCeIkdpos3TrtUHOlFJUMyckKI9cYZDggRN0_KS7nX19gq3d5ThC_mkTRPsbSHljIbeFBrSA3qMwwTgvhTdcexoUGAhcSyEYa14fZ69dTj_2WKrdpn2e2vqWGa05M1TTv6wNNNM4hVQzuDEWZ1dKayY4paSxzl9htfI4RteyC7Hh_wjoLHA5lZIxWBfnyzdhHCwl9hC0fRF003z6T_N8gNfYvwAICKn2
CitedBy_id	crossref_primary_10_1145_3702638 crossref_primary_10_1109_ACCESS_2024_3522961
Cites_doi	10.1007/978-3-319-24574-4_28 10.1109/ACCESS.2021.3116265 10.1109/CVPR46437.2021.00788 10.24963/ijcai.2021/112 10.1038/s41592-021-01249-6 10.1007/978-3-030-32778-1_10 10.1109/CVPR.2019.00453 10.1007/978-3-658-25326-4_7 10.1109/CVPR.2017.17 10.1016/j.cmpb.2022.107333 10.1109/TIP.2020.2973510 10.1109/WACV51458.2022.00181 10.1109/ICCV.2017.167 10.1016/j.techfore.2021.121127 10.1148/rg.256055018 10.1109/CVPR52688.2022.02007 10.1109/WACV48630.2021.00113 10.3390/app11094233
ContentType	Journal Article
Copyright	COPYRIGHT 2024 MDPI AG 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: COPYRIGHT 2024 MDPI AG – notice: 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION ABUWG AFKRA AZQEC BENPR CCPQU DWQXO PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI DOA
DOI	10.3390/app14062576
DatabaseName	CrossRef ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest ProQuest One Community College ProQuest Central Korea Proquest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Publicly Available Content Database ProQuest Central ProQuest One Academic Middle East (New) ProQuest One Academic UKI Edition ProQuest Central Essentials ProQuest Central Korea ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	CrossRef Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Sciences (General) Statistics
EISSN	2076-3417
ExternalDocumentID	oai_doaj_org_article_aedde49f9cd64d938d1f7a9af3864422 A788243110 10_3390_app14062576
GeographicLocations	Germany
GeographicLocations_xml	– name: Germany
GroupedDBID	.4S 2XV 5VS 7XC 8CJ 8FE 8FG 8FH AADQD AAFWJ AAYXX ADBBV ADMLS AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS APEBS ARCSS BCNDV BENPR CCPQU CITATION CZ9 D1I D1J D1K GROUPED_DOAJ IAO IGS ITC K6- K6V KC. KQ8 L6V LK5 LK8 M7R MODMG M~E OK1 P62 PHGZM PHGZT PIMPY PROAC TUS ABUWG AZQEC DWQXO PKEHL PQEST PQQKQ PQUKI
ID	FETCH-LOGICAL-c497t-b17143e94f16d5f7e4d0eac409689895cbb9e32777182c46a7de37ef6ada30ec3
IEDL.DBID	PIMPY
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001191326500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2076-3417
IngestDate	Tue Oct 14 19:05:13 EDT 2025 Mon Jun 30 14:44:08 EDT 2025 Tue Nov 11 11:08:58 EST 2025 Tue Nov 04 18:23:25 EST 2025 Sat Nov 29 07:14:47 EST 2025 Tue Nov 18 22:34:29 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c497t-b17143e94f16d5f7e4d0eac409689895cbb9e32777182c46a7de37ef6ada30ec3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0004-5453-3731 0000-0002-3049-035X 0000-0001-7850-9913 0000-0002-6566-1382 0000-0002-7747-4293
OpenAccessLink	https://www.proquest.com/publiccontent/docview/2988329181?pq-origsite=%requestingapplication%
PQID	2988329181
PQPubID	2032433
ParticipantIDs	doaj_primary_oai_doaj_org_article_aedde49f9cd64d938d1f7a9af3864422 proquest_journals_2988329181 gale_infotracmisc_A788243110 gale_infotracacademiconefile_A788243110 crossref_citationtrail_10_3390_app14062576 crossref_primary_10_3390_app14062576
PublicationCentury	2000
PublicationDate	2024-03-01
PublicationDateYYYYMMDD	2024-03-01
PublicationDate_xml	– month: 03 year: 2024 text: 2024-03-01 day: 01
PublicationDecade	2020
PublicationPlace	Basel
PublicationPlace_xml	– name: Basel
PublicationTitle	Applied sciences
PublicationYear	2024
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	Edlund (ref_8) 2021; 18 ref_14 ref_13 ref_12 ref_11 Habijan (ref_7) 2021; 9 ref_10 Aguirre (ref_20) 2005; 25 ref_31 Zuo (ref_4) 2021; 173 ref_30 ref_19 ref_18 ref_17 Zhou (ref_1) 2020; 29 ref_16 ref_15 ref_25 ref_24 ref_23 ref_22 ref_21 ref_3 ref_2 ref_29 ref_28 ref_27 ref_26 ref_9 ref_5 ref_6
References_xml	– ident: ref_30 – ident: ref_3 – ident: ref_28 doi: 10.1007/978-3-319-24574-4_28 – volume: 9 start-page: 133365 year: 2021 ident: ref_7 article-title: Training on polar image transformations improves biomedical image segmentation publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3116265 – ident: ref_26 – ident: ref_24 doi: 10.1109/CVPR46437.2021.00788 – ident: ref_11 – ident: ref_2 doi: 10.24963/ijcai.2021/112 – ident: ref_16 – volume: 18 start-page: 1038 year: 2021 ident: ref_8 article-title: LIVECell—A large-scale dataset for label-free live cell segmentation publication-title: Nat. Methods doi: 10.1038/s41592-021-01249-6 – ident: ref_14 doi: 10.1007/978-3-030-32778-1_10 – ident: ref_18 – ident: ref_25 doi: 10.1109/CVPR.2019.00453 – ident: ref_6 doi: 10.1007/978-3-658-25326-4_7 – ident: ref_21 – ident: ref_12 doi: 10.1109/CVPR.2017.17 – ident: ref_9 doi: 10.1016/j.cmpb.2022.107333 – volume: 29 start-page: 4516 year: 2020 ident: ref_1 article-title: One-pass multi-task networks with cross-task guided attention for brain tumor segmentation publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2020.2973510 – ident: ref_10 doi: 10.1109/WACV51458.2022.00181 – ident: ref_31 – ident: ref_29 – ident: ref_22 doi: 10.1109/ICCV.2017.167 – ident: ref_27 – volume: 173 start-page: 121127 year: 2021 ident: ref_4 article-title: Curvature-based feature selection with application in classifying electronic health records publication-title: Technol. Forecast. Soc. Chang. doi: 10.1016/j.techfore.2021.121127 – volume: 25 start-page: 1501 year: 2005 ident: ref_20 article-title: Abdominal wall hernias: Imaging features, complications, and diagnostic pitfalls at multi–detector row CT publication-title: Radiographics doi: 10.1148/rg.256055018 – ident: ref_5 doi: 10.1109/CVPR52688.2022.02007 – ident: ref_15 – ident: ref_23 doi: 10.1109/WACV48630.2021.00113 – ident: ref_17 – ident: ref_19 – ident: ref_13 doi: 10.3390/app11094233
SSID	ssj0000913810
Score	2.3039277
Snippet	Deep learning-based segmentation models have made a profound impact on medical procedures, with U-Net based computed tomography (CT) segmentation models...
SourceID	doaj proquest gale crossref
SourceType	Open Website Aggregation Database Enrichment Source Index Database
StartPage	2576
SubjectTerms	adversarial attacks computed tomography (CT) segmentation CT imaging data augmentation Deep learning deep learning-based segmentation Medical research Medical screening Methods realistic adversarial samples Standard deviation Statistics Tomography
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEB5EPOhBfOL6IgfBBxTbpNs0x1UUTyKoIF5CmocIuiu7q7_fmTRKFxQvXpM5pJN5fEM63wAcmMY5pxqeWQSrWSlCkSknbFZxI4xASCedicMm5PV1_fCgbjqjvuifsJYeuFXcqfHogKUKyrqqdErUrgjSKBNEjamcx-ibS9UppmIMVgVRV7UNeQLrenoPxlqiInw9k4IiU_9v8TgmmcsVWE7okA3aU63CnB-uwVKHM3ANVpM3TthRoow-XofHOFd5Ysia2GA6pcZ5Nhqy9AzDbv3Ta2oywkUafsM-ng2766BW3BgFRojwfewZYdCWwnkD7i8v7s6vsjQ1IbOlktOsiSPNvSpDUbl-kL50OUZXrOMqGhXZt02jvOBSYlbitqyMdF5IHyrjjMi9FZswPxwN_RYwwZ3sO6GIg7m0tcfajBCTxcTncxmKHpx8KVLbRClOky1eNJYWpHXd0XoPDr6F31omjZ_FzuhGvkWI_jouoFHoZBT6L6PowSHdpyYnxQNZk3oN8LOI7koPsPDnCJ2KvAe7M5LoXHZ2-8sidHLuieaqxjioEBtt_8dhd2CRI1Jqf2zbhfnp-N3vwYL9wHse70e7_gQODf1k priority: 102 providerName: Directory of Open Access Journals
Title	Adversarial Attacks on Medical Segmentation Model via Transformation of Feature Statistics
URI	https://www.proquest.com/docview/2988329181 https://doaj.org/article/aedde49f9cd64d938d1f7a9af3864422
Volume	14
WOSCitedRecordID	wos001191326500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 2076-3417 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913810 issn: 2076-3417 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NbxMxEB2VhAMc6AdUBNrIh0oFpFV37c16farSqhUciCJapMLF8vqjqlSyJUn7-5nZddJEopy4rn3wasYzb2zPewAHpnLOqYonFsFqkouQJcoJmxTcCCMQ0klnGrEJORqVV1dqHNujZ_FZ5SImNoG6ZXumd9sYhI9cbenE_IirEl1RYXo6vvudkIYU3bVGQY1n0CXirbQD3fGXr-MfyzMX4sAss7Rt0xNY7dMtMVYYBaHutcTU8Pc_FaWb1HO--X8XvQWvIgRlw9ZntmHDT3bg5Qox4Q5sxy0_Yx8iL_XH1_CzEW-eGXJZNpzPqTuf1RMW73rYhb_-FTuZ8CMp7LCHG8MuV6AxDtSBEey8n3pGQLfliX4D38_PLk8_J1GaIbG5kvOkanTTvcpDVrhBkD53KYZwLBYL0qMc2KpSXnApMfVxmxdGOi-kD4VxRqTeil3oTOqJfwtMcCcHTigies5t6bEAJFhmMbv6VIasB58WdtE28paTfMatxvqFjKhXjNiDg-Xku5au4-_TTsjAyynEsd18qKfXOm5ZbTyG_lwFZV2ROyVKlwVplAmiRBDJeQ8OyT00RQJckDWxoQF_izi19FCiqyM-y9Ie7K3NxB1s14cX3qNjBJnpR2d59-_h9_CCI9Bq38XtQWc-vff78Nw-oAWnfeienI3G3_rNWUM_bog_5GoaFQ
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1db9MwFL0aHRLjAdgAURjghyE-pIjETuP4AaHyMa3aVlWiSBsvxrGdaRI0o-2G-FP8Ru5NnNJKwNseeI2tKImP7z03ts8B2DGFc04VPLJIVqNUlEmknLBRxo0wAimddKY2m5DDYX50pEZr8LM9C0PbKtuYWAdqV1n6R_6SqxzBpzAhvT77FpFrFK2uthYaDSz2_Y_vWLLNXg3e4fg-4Xz3_fjtXhRcBSKbKjmPitry26u0TDLXK6VPXYzRB-ucjKwUe7YolBdcSoza3KaZkc4L6cvMOCNibwXe9wqspwj2uAPro8Hh6HjxV4dUNvMkbg4CCqFiWofGGiYjXr-S-mqHgL_lgTq57d783z7LLbgRaDTrN7jfhDU_2YLrS-KKW7AZwtaMPQva2s9vw6fagHpmaNqx_nxOCgOsmrCwXsU--JOv4TQWXiSXIHZxath4id5jQ1Uyos7nU8-IrDda13fg46W88V3oTKqJvwdMcCd7TigSq05t7rGIJWppkSH4WJZJF160I69t0F4nC5AvGmswgolegkkXdhadzxrJkT93e0MQWnQhnfD6QjU90SHsaOMxfaWqVNZlqVMid0kpjTKlyJEIc96FpwRATdEMH8iacCgDX4t0wXRf4nRFjpnEXdhe6YlRyK42t_jUIQrO9G9w3v9382O4tjc-PNAHg-H-A9jgSBybfX7b0JlPz_1DuGovcDSnj8KEY_D5ssH8C0AqaZs
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1db9MwFL0aHULwAGyAKAzwwxAfUrTETuP4AaHCqKgGVSWGNHgxjj8mJGhG2w3x1_h13Ju4pZWAtz3wGltREh_fe25snwOwayrnnKp4YpGsJrkIWaKcsEnBjTACKZ10pjGbkKNReXSkxhvwc3EWhrZVLmJiE6hdbekf-R5XJYJPYULaC3FbxHh_8PzkW0IOUrTSurDTaCFy4H98x_Jt9my4j2P9kPPBq8OXr5PoMJDYXMl5UjX2317lIStcL0ifuxQjEdY8Bdkq9mxVKS-4lBjBuc0LI50X0ofCOCNSbwXe9wJsSvLv7cDmePh2_GH5h4cUN8ssbQ8FCqFSWpPGeqYgjr-WBhu3gL_lhCbRDa79z5_oOlyN9Jr12_mwBRt-sg1XVkQXt2ErhrMZexw1t5_cgI-NMfXM0HRk_fmclAdYPWFxHYu988df4yktvEjuQezss2GHK7QfG-rAiFKfTj0jEt9qYN-E9-fyxregM6kn_jYwwZ3sOaFIxDq3pcfiliinRebgUxmyLjxdoEDbqMlO1iBfNNZmBBm9Apku7C47n7RSJH_u9oLgtOxC-uHNhXp6rGM40sZjWstVUNYVuVOidFmQRpkgSiTInHfhEYFRU5TDB7ImHtbA1yK9MN2XOI2Re2ZpF3bWemJ0suvNC6zqGB1n-jdQ7_y7-QFcQgTrN8PRwV24zJFPttv_dqAzn576e3DRnuFgTu_Hucfg03lj-Re8lXJk
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=Adversarial+Attacks+on+Medical+Segmentation+Model+via+Transformation+of+Feature+Statistics&rft.jtitle=Applied+sciences&rft.au=Lee%2C+Woonghee&rft.au=Ju%2C+Mingeon&rft.au=Sim%2C+Yura&rft.au=Young%2C+Kul+Jung&rft.date=2024-03-01&rft.pub=MDPI+AG&rft.eissn=2076-3417&rft.volume=14&rft.issue=6&rft.spage=2576&rft_id=info:doi/10.3390%2Fapp14062576&rft.externalDBID=HAS_PDF_LINK
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2076-3417&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2076-3417&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2076-3417&client=summon