On the Economics of Adversarial Machine Learning
Given the widespread deployment of machine learning algorithms, the security of these algorithms and thus, the field of adversarial machine learning gained popularity in the research community. In this article, we loosen several unrealistic restrictions found in prior art and bring economical-inspir...
Uloženo v:
| Vydáno v: | IEEE transactions on information forensics and security Ročník 19; s. 4670 - 4685 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
New York
IEEE
2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 1556-6013, 1556-6021 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Given the widespread deployment of machine learning algorithms, the security of these algorithms and thus, the field of adversarial machine learning gained popularity in the research community. In this article, we loosen several unrealistic restrictions found in prior art and bring economical-inspired adversarial machine learning one step closer to being applicable in the real world. First, we extend our own game-theoretical framework such that it allows any arbitrary number of actions for both actors, and analytically determine equilibrium strategies and conditions where mixed strategies are expected for the specific case in which both actors choose from any two arbitrary actions. Then, we pay special attention to an adversary's knowledge about the attacked system by modeling them as a white-, gray-, or black-box adversary. We conduct extensive experiments for three architectures, two training procedures, and four adversarial attacks in different variations as direct and transfer attacks, resulting in 300 data points consisting of the respective accuracy and robustness values and the computational costs for both actors. We then instantiate our model with this data and explore the structure of the game for a wide range of each game parameter, overcoming the complexity by applying algorithmic game theory. We discover surprising properties in the actors' strategies, such as the feasibility of cheap attacks that have been dismissed as practically irrelevant so far - examples include universal adversarial perturbations or (transfer) attacks utilizing only few optimization steps. For the defender, we find that given recent attacks and countermeasures, a rational defender would try to hide as much as possible from their infrastructure. |
|---|---|
| AbstractList | Given the widespread deployment of machine learning algorithms, the security of these algorithms and thus, the field of adversarial machine learning gained popularity in the research community. In this article, we loosen several unrealistic restrictions found in prior art and bring economical-inspired adversarial machine learning one step closer to being applicable in the real world. First, we extend our own game-theoretical framework such that it allows any arbitrary number of actions for both actors, and analytically determine equilibrium strategies and conditions where mixed strategies are expected for the specific case in which both actors choose from any two arbitrary actions. Then, we pay special attention to an adversary’s knowledge about the attacked system by modeling them as a white-, gray-, or black-box adversary. We conduct extensive experiments for three architectures, two training procedures, and four adversarial attacks in different variations as direct and transfer attacks, resulting in 300 data points consisting of the respective accuracy and robustness values and the computational costs for both actors. We then instantiate our model with this data and explore the structure of the game for a wide range of each game parameter, overcoming the complexity by applying algorithmic game theory. We discover surprising properties in the actors’ strategies, such as the feasibility of cheap attacks that have been dismissed as practically irrelevant so far - examples include universal adversarial perturbations or (transfer) attacks utilizing only few optimization steps. For the defender, we find that given recent attacks and countermeasures, a rational defender would try to hide as much as possible from their infrastructure. |
| Author | Merkle, Florian Samsinger, Maximilian Pevny, Tomas Schottle, Pascal |
| Author_xml | – sequence: 1 givenname: Florian orcidid: 0000-0003-3562-5265 surname: Merkle fullname: Merkle, Florian email: florian.merkle@uibk.ac.at organization: Department of Information Systems, Productions and Logistic, University of Innsbruck, Innsbruck, Austria – sequence: 2 givenname: Maximilian orcidid: 0000-0002-8521-8142 surname: Samsinger fullname: Samsinger, Maximilian email: m.samsinger@gmail.com organization: Department of Digital Business and Software Engineering, MCI Innsbruck, Innsbruck, Austria – sequence: 3 givenname: Pascal orcidid: 0000-0001-8710-9188 surname: Schottle fullname: Schottle, Pascal email: pascal.schoettle@mci.edu organization: Department of Digital Business and Software Engineering, MCI Innsbruck, Innsbruck, Austria – sequence: 4 givenname: Tomas orcidid: 0000-0002-5768-9713 surname: Pevny fullname: Pevny, Tomas email: pevnytom@fel.cvut.cz organization: Department of Computer Science, Czech Technical University in Prague, Prague, Czech Republic |
| BookMark | eNp9kE1rAjEQhkOxULX9AYUeFnpem4_dZHMUUStYPNSeQzY7qRFNbLIW-u-7opTSQ08zh_eZd3gGqOeDB4TuCR4RguXTejF7HVFMixFjQlZUXqE-KUuec0xJ72cn7AYNUtpiXBSEV32EVz5rN5BNTfBh70zKgs3GzSfEpKPTu-xFm43zkC1BR-_8-y26tnqX4O4yh-htNl1PnvPlar6YjJe56R5oc1PLWgoujMWGN8wKQSQ0nNaVoYSBMBiINKLBuuGWGq6JLQvLi6amGnNo2BA9nu8eYvg4QmrVNhyj7yoVwyUlFWOV7FLknDIxpBTBqkN0ex2_FMHqJEadxKiTGHUR0zHiD2Ncq1sXfBu12_1LPpxJBwC_mgrBCynZN_RgccE |
| CODEN | ITIFA6 |
| CitedBy_id | crossref_primary_10_1109_TVT_2024_3432614 |
| Cites_doi | 10.1007/978-3-030-01258-8_39 10.1109/TIFS.2015.2509941 10.1109/CVPR.2017.17 10.1007/978-3-319-68711-7_21 10.1145/1143844.1143889 10.1126/science.1130992 10.1145/2020408.2020495 10.1609/aaai.v35i6.16641 10.2307/1969529 10.1016/j.ijpe.2008.04.002 10.1109/sp.2017.49 10.1145/3411508.3421376 10.1145/1014052.1014066 10.1109/SP40000.2020.00045 10.1145/3437880.3460407 10.1109/CVPRW.2018.00211 10.1007/s10994-010-5188-5 10.1007/978-3-642-17197-0_9 10.1016/j.patcog.2018.07.023 10.23919/EUSIPCO.2018.8553214 10.1109/SaTML54575.2023.00031 10.1109/cvpr.2018.00474 10.1109/CVPR.2009.5206848 10.1007/978-3-319-46493-0_38 10.1109/TIFS.2012.2237397 10.1007/978-3-030-90370-1_9 10.2200/s00108ed1v01y200802aim003 10.1007/978-3-642-40994-3_25 10.1109/CVPR.2016.282 10.1109/TIFS.2017.2718494 10.1137/0112064 10.1109/ACSAC.2001.991552 10.1109/TIFS.2009.2019154 10.1145/1161366.1161393 10.1145/3128572.3140448 10.48550/ARXIV.1706.06083 10.1109/CVPR.2017.243 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 KR7 L7M L~C L~D |
| DOI | 10.1109/TIFS.2024.3379829 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Civil Engineering Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1556-6021 |
| EndPage | 4685 |
| ExternalDocumentID | 10_1109_TIFS_2024_3379829 10476499 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Czech Science Foundation (GACR) grantid: 19-29680L; 22-32620S funderid: 10.13039/501100001824 – fundername: Austrian Science Fund (FWF) grantid: I 4057-N31 funderid: 10.13039/501100002428 – fundername: Czech Science Foundation grantid: 22-32620S funderid: 10.13039/501100001824 |
| GroupedDBID | 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 KR7 L7M L~C L~D |
| ID | FETCH-LOGICAL-c337t-cb9b9767cf0c6d3f7719ed62b8c213e7c0e19c7d0ad6f2c6a1f54f64db2a06ed3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001216477200028&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1556-6013 |
| IngestDate | Mon Jun 30 05:15:53 EDT 2025 Tue Nov 18 22:14:28 EST 2025 Sat Nov 29 02:51:35 EST 2025 Wed Aug 27 02:05:27 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://creativecommons.org/licenses/by/4.0/legalcode |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c337t-cb9b9767cf0c6d3f7719ed62b8c213e7c0e19c7d0ad6f2c6a1f54f64db2a06ed3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-8521-8142 0000-0003-3562-5265 0000-0001-8710-9188 0000-0002-5768-9713 |
| OpenAccessLink | https://ieeexplore.ieee.org/document/10476499 |
| PQID | 3052183389 |
| PQPubID | 85506 |
| PageCount | 16 |
| ParticipantIDs | ieee_primary_10476499 proquest_journals_3052183389 crossref_citationtrail_10_1109_TIFS_2024_3379829 crossref_primary_10_1109_TIFS_2024_3379829 |
| PublicationCentury | 2000 |
| PublicationDate | 20240000 2024-00-00 20240101 |
| PublicationDateYYYYMMDD | 2024-01-01 |
| PublicationDate_xml | – year: 2024 text: 20240000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on information forensics and security |
| PublicationTitleAbbrev | TIFS |
| PublicationYear | 2024 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref57 Carlini (ref42) 2019 ref56 ref15 ref58 ref53 Zhang (ref2) ref11 ref55 ref54 ref16 ref19 ref18 ref50 Pang (ref3) Athalye (ref21) Grosse (ref41) ref46 ref45 Xiao (ref61) Brendel (ref14) ref48 Cohen (ref23) ref47 Gilmer (ref39) 2018 Biggio (ref9) ref44 Pinot (ref37) ref43 ref49 ref8 ref7 Jacobsen (ref59) ref6 ref5 ref40 ref35 ref34 ref31 ref30 ref33 Szegedy (ref12) ref32 ref1 Tramer (ref22); 33 Pita (ref25) Robey (ref38) Brückner (ref10) 2012; 13 Kerckhoffs (ref62) 1883; 9 Papernot (ref17) 2016 Shapiro (ref26) 1999 ref20 Wong (ref24) Krizhevsky (ref51) 2009 Loshchilov (ref52) ref28 Zhao (ref4) 2023 ref27 ref29 ref60 Meunier (ref36) |
| References_xml | – ident: ref18 doi: 10.1007/978-3-030-01258-8_39 – ident: ref32 doi: 10.1109/TIFS.2015.2509941 – start-page: 7472 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref2 article-title: Theoretically principled trade-off between robustness and accuracy – ident: ref6 doi: 10.1109/CVPR.2017.17 – ident: ref33 doi: 10.1007/978-3-319-68711-7_21 – ident: ref34 doi: 10.1145/1143844.1143889 – ident: ref28 doi: 10.1126/science.1130992 – start-page: 7717 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref37 article-title: Randomization matters how to defend against strong adversarial attacks – year: 2016 ident: ref17 article-title: Transferability in machine learning: From phenomena to black-box attacks using adversarial samples publication-title: arXiv:1605.07277 – volume: 9 start-page: 5 issue: 1 year: 1883 ident: ref62 article-title: La cryptographie militaire publication-title: J. Des. Sci. Militaires – volume-title: Learning Multiple Layers of Features From Tiny Images year: 2009 ident: ref51 – year: 2023 ident: ref4 article-title: Mitigating the accuracyrobustness trade-off via multi-teacher adversarial distillation publication-title: arXiv:2306.16170 – start-page: 17258 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref3 article-title: Robustness and accuracy could be reconcilable by definition – ident: ref8 doi: 10.1145/2020408.2020495 – year: 2018 ident: ref39 article-title: Motivating the rules of the game for adversarial example research publication-title: arXiv:1807.06732 – ident: ref56 doi: 10.1609/aaai.v35i6.16641 – ident: ref46 doi: 10.2307/1969529 – ident: ref55 doi: 10.1016/j.ijpe.2008.04.002 – ident: ref16 doi: 10.1109/sp.2017.49 – volume: 13 start-page: 2617 issue: 1 year: 2012 ident: ref10 article-title: Static prediction games for adversarial learning problems publication-title: J. Mach. Learn. Res. – start-page: 1 volume-title: Proc. The 12th Int. Conf. Learn. Represent. ident: ref38 article-title: Adversarial training should be cast as a non-zero-sum game – ident: ref44 doi: 10.1145/3411508.3421376 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref61 article-title: Spatially transformed adversarial examples – ident: ref1 doi: 10.1145/1014052.1014066 – start-page: 1310 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref23 article-title: Certified adversarial robustness via randomized smoothing – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref14 article-title: Decision-based adversarial attacks: Reliable attacks against black-box machine learning models – start-page: 1884 volume-title: Proc. AAAI ident: ref25 article-title: Armor security for Los Angeles international airport – ident: ref53 doi: 10.1109/SP40000.2020.00045 – ident: ref57 doi: 10.1145/3437880.3460407 – ident: ref60 doi: 10.1109/CVPRW.2018.00211 – ident: ref7 doi: 10.1007/s10994-010-5188-5 – start-page: 7677 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref36 article-title: Mixed Nash equilibria in the adversarial examples game – ident: ref30 doi: 10.1007/978-3-642-17197-0_9 – start-page: 1 volume-title: Proc. 39th Int. Conf. Mach. Learn. ident: ref41 article-title: ‘Why do so?’—A practical perspective on machine learning security – ident: ref13 doi: 10.1016/j.patcog.2018.07.023 – ident: ref58 doi: 10.23919/EUSIPCO.2018.8553214 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref12 article-title: Intriguing properties of neural networks – ident: ref40 doi: 10.1109/SaTML54575.2023.00031 – volume-title: Information Rules: A Strategic Guide To the Network Economy year: 1999 ident: ref26 – ident: ref49 doi: 10.1109/cvpr.2018.00474 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref24 article-title: Fast is better than free: Revisiting adversarial training – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref52 article-title: SGDR: Stochastic gradient descent with warm restarts – ident: ref20 doi: 10.1109/CVPR.2009.5206848 – ident: ref48 doi: 10.1007/978-3-319-46493-0_38 – start-page: 274 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref21 article-title: Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples – volume: 33 start-page: 1633 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref22 article-title: On adaptive attacks to adversarial example defenses – ident: ref31 doi: 10.1109/TIFS.2012.2237397 – ident: ref5 doi: 10.1007/978-3-030-90370-1_9 – year: 2019 ident: ref42 article-title: On evaluating adversarial robustness publication-title: arXiv:1902.06705 – ident: ref45 doi: 10.2200/s00108ed1v01y200802aim003 – ident: ref11 doi: 10.1007/978-3-642-40994-3_25 – ident: ref43 doi: 10.1109/CVPR.2016.282 – ident: ref35 doi: 10.1109/TIFS.2017.2718494 – ident: ref47 doi: 10.1137/0112064 – ident: ref27 doi: 10.1109/ACSAC.2001.991552 – start-page: 1467 volume-title: Proc. Int. Conf. Mach. Learn. (ICML) ident: ref9 article-title: Poisoning attacks against support vector machines – start-page: 1 volume-title: Proc. Int. Conf. Learn. Represent. ident: ref59 article-title: Excessive invariance causes adversarial vulnerability – ident: ref29 doi: 10.1109/TIFS.2009.2019154 – ident: ref54 doi: 10.1145/1161366.1161393 – ident: ref19 doi: 10.1145/3128572.3140448 – ident: ref15 doi: 10.48550/ARXIV.1706.06083 – ident: ref50 doi: 10.1109/CVPR.2017.243 |
| SSID | ssj0044168 |
| Score | 2.4085796 |
| Snippet | Given the widespread deployment of machine learning algorithms, the security of these algorithms and thus, the field of adversarial machine learning gained... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 4670 |
| SubjectTerms | Adversarial machine learning Algorithms Computational modeling Data points economics of information security Game theory Games Machine learning Perturbation methods Robustness Training |
| Title | On the Economics of Adversarial Machine Learning |
| URI | https://ieeexplore.ieee.org/document/10476499 https://www.proquest.com/docview/3052183389 |
| Volume | 19 |
| WOSCitedRecordID | wos001216477200028&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1556-6021 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0044168 issn: 1556-6013 databaseCode: RIE dateStart: 20060101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH7o8KAHp3PidEoOnoRu6a-kPYo4FHQKTtitpMmLCLLJuvn3m6SpDkTBWw9Jab-X5H0vyfcewHnJteFsoQ4ijNAEKCgCgYbIpVZYorNEsMwJhe_4eJxNp_mjF6s7LQwiustnOLCP7ixfzeXKbpUNbVoBZij6JmxyzmqxVrPsGrde697SlAUmyoj9EWZI8-HkdvRkQsEoGcQxzzNHJ7-dkKuq8mMpdv5l1P7nl-3BrieS5LK2_D5s4KwD7aZIA_FztgM7axkHD4A-zIihfKTRI1dkrokrylwJOxTJvbtcicTnXX3pwvPoenJ1E_iiCYE0P7cMZJmXhmJwqalkKjaWCHNULCozGYUxckkxzCVXVCimI8lEqNNEs0SVkaAMVXwIrdl8hkdAhAmlDF2IdCJUEmJcUtShsvlfWEK14D2gDYqF9BnFbWGLt8JFFjQvLPCFBb7wwPfg4qvLe51O46_GXYv0WsMa5B70G1sVfsZVRWxVyJkJuPPjX7qdwLZ9e71_0ofWcrHCU9iSH8vXanHmBtMnHjLF5w |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH74C9SD06k4nZqDJ6GatmnaHkUcitsUnLBbSZMXEWQTO_37TdJUB6LgrYeEtu8led-X5HsP4KRMtcFsoQ4ijNAQFBSBQAPkEiss0RkTPHNC4X46HGbjcX7vxepOC4OI7vIZntlHd5avpvLdbpWd27QC3ED0RVhOmCE-tVyrWXhNYK-Vb0nCA8MzYn-IGdL8fHTTezBkMGJncZzmmQOU32HI1VX5sRi7CNNr_fPbNmHDQ0lyUft-CxZw0oZWU6aB-FnbhvW5nIPbQO8mxIA-0iiSKzLVxJVlroQdjGTgrlci8ZlXn3bgsXc1urwOfNmEQJqfmwWyzEsDMlKpqeQqNr4Ic1Q8KjMZhTGmkmKYy1RRobiOJBehTpjmTJWRoBxVvAtLk-kE94AIQ6YMYIg0E4qFGJcUdahsBhjOqBZpB2hjxUL6nOK2tMVL4bgFzQtr-MIavvCG78DpV5fXOqHGX413rKXnGtZG7kC38VXh51xVxFaHnBnKne__0u0YVq9Hg37RvxneHsCafVO9m9KFpdnbOx7CivyYPVdvR25gfQKXm8ku |
| 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=On+the+Economics+of+Adversarial+Machine+Learning&rft.jtitle=IEEE+transactions+on+information+forensics+and+security&rft.au=Merkle%2C+Florian&rft.au=Samsinger%2C+Maximilian&rft.au=Sch%C3%B6ttle%2C+Pascal&rft.au=Pevny%2C+Tomas&rft.date=2024&rft.issn=1556-6013&rft.eissn=1556-6021&rft.volume=19&rft.spage=4670&rft.epage=4685&rft_id=info:doi/10.1109%2FTIFS.2024.3379829&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIFS_2024_3379829 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1556-6013&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1556-6013&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1556-6013&client=summon |