Palmprint false acceptance attack with a generative adversarial network (Gan)

Fei Wang, Lu Leng, Andrew Beng Jin Teoh, Jun Chu

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Biometric-based authentication is widely deployed on multimedia systems currently; however, biometric systems are vulnerable to image-level attacks for impersonation. Reconstruction attack (RA) and presentation attack (PA) are two typical instances for image-level attacks. In RA, the reconstructed images often have insufficient naturalness due to the presence of remarkable counterfeit appearance, thus their forgeries can be easily detected by machine or human. The PA requires genuine users’ original images, which are difficult to acquire in practice and to counterfeit fake biometric images on spoofing carriers. In this paper, we develop false acceptance attack (FAA) for a palmprint biometric, which overcomes the aforementioned problems of RA and PA. FAA does not require genuine users’ images, and it can be launched simply with the synthetic images with high naturalness, which are generated by the generative adversarial networks. As a case study, we demonstrate the feasibility of FAA against coding-based palmprint biometric systems. To further improve the efficiency of FAA, we employ a clustering method to select diverse fake images in order to enhance the diversity of the fake images used, so the number of attack times is reduced. Our experimental results show the success rate and effectiveness of the FAA.

Original languageEnglish
Article number8547
Pages (from-to)1-16
Number of pages16
JournalApplied Sciences (Switzerland)
Volume10
Issue number23
DOIs
Publication statusPublished - 2020 Dec 1

Bibliographical note

Funding Information:
In our future work, we will modify and improve GAN to enhance diversity to further increase the attack success rate. We will also try to develop more strategies to decrease the number of attack times. future work, we will modify and improve GAN to enhance diversity to further increase the attack success rate. We will also try to develop more strategies to decrease the number of attack times. validation, L.L. and J.C.; formal analysis, L.L., F.W. and A.B.J.T.; investigation, L.L. and F.W.; resources, L.L. and F.W.; data curation, F.W.; writing—original draft preparation, F.W.; writing—review and editing, L.L., J.C. and validAa.tBio.J.nT,.;L v.Lis.uaanlidzaJt.iCon.;, fFo.Wrm.;a sluapnearlyvssiiiosn, L, L.L.L.,.;F p.Wro.jeacnt dadAm.Bin.Ji.sTtr.;aitniovne,sLt.iLg.a; tfiuonnd,iLn.gLa.caqnudisiFt.iWon.,; Jr.eCs.oAulrlcaeust,hLo.Lrs. and F.W.h; advaeta recaudra atniodna g, Fre.Wed.; two rtihteipnug—blisohriegdi vnearlsdiornaf ot fp trheep amraatniuonsc,rFi.pWt.. ; writing—review and editing, L.L., J.C. and A.B.J.T.; visualization, F.W.; supervision, L.L.; project administration, L.L.; funding acquisition, J.C. All authors Funding: This work was supported in part by the National Natural Science Foundation of China (61866028, 61663031), Key Program Project of Research and Development (Jiangxi Provincial Department of Science and Technology) (20171ACE50024, 20192BBE50073) Foundationof China Scholarship Council (CSC201908360075). 61663031), Key Program Project of Research and Development (Jiangxi Provincial Department of Science and TechCnoonlofgliyc)ts(2 o0f1 I7n1tAeCreEs5tT:0h0e2a4u,t2h0o1r9s2 dBeBclEa5re0 0n7o3c)oFnofulicntd oaf tiinotneroefsCt.hina Scholarship Council (CSC201908360075).

Funding Information:
This work was supported in part by the National Natural Science Foundation of China (61866028, 61663031), Key Program Project of Research and Development (Jiangxi Provincial Department of Science and Technology) (20171ACE50024, 20192BBE50073) Foundation of China Scholarship Council (CSC201908360075).

Publisher Copyright:
© 2020 by the authors. Licensee MDPI, Basel, Switzerland.

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Fingerprint

Dive into the research topics of 'Palmprint false acceptance attack with a generative adversarial network (Gan)'. Together they form a unique fingerprint.

Cite this