Dynamic random projection for biometric template protection

Yang, Bian; Hartung, Daniel; Simoens, Koen; Busch, Christoph

doi:10.1109/btas.2010.5634538

Cited by 87 publications

(66 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main challenge, as we mentioned in section 2, for a honey based system is to generate honey objects, in our case synthetic face templates, which cannot be distinguished from real templates. The protection mechanism we have adopted on the faces' feature vectors, is the plain-feature-defined sub-set selection borrowed by the idea in [12]. Recognition performance degradation can be anticipated from the adoption of BTPS as discussed in [13].…”

Section: Honey Face Templatesmentioning

confidence: 99%

Protected Honey Face Templates

Martiri

Yang

Busch

2015

2015 International Conference of the Biometrics Special Interest Group (BIOSIG)

Self Cite

View full text Add to dashboard Cite

Most existing biometric template protection schemes (BTPS) do not provide as strong security as cryptographic tools; and furthermore, they are rarely able to detect during a verification process whether a probe template has been leaked from the database or not (i.e., being used by an imposter or a genuine user). By using the "honeywords" idea, which was proposed to detect the cracking of hashed password database, we show in this paper how to enable the detectability of biometric template database leakage. We add an extra layer of protection since biometric features cannot be renewed. The biometric system design implies that protection mechanisms must satisfy the irreversibility property and to this respect we apply different correlation tests to show the non-distinguishability between genuine and honey templates. In this paper we implement the idea of a honey template protection scheme on faces and evaluate the security and accuracy performance.

show abstract

Section: Honey Face Templatesmentioning

confidence: 99%

Protected Honey Face Templates

Martiri

Yang

Busch

2015

2015 International Conference of the Biometrics Special Interest Group (BIOSIG)

Self Cite

View full text Add to dashboard Cite

show abstract

“…They also showed that the attack complexity is considerably low (e.g., only 2 17 attempts are required when the random offsets table is known with reference to 2 120 attempts when the random offsets table absent). Although Yang et al [9] later proposed a dynamic random projection that was originally outlined in Teoh et al [10], to alleviate this problem, dynamic random projection incurs substantially increased computation cost than that of random offsets used in [7].…”

Section: A Minutiae-based Fingerprint Cancelable Templatementioning

confidence: 99%

“…In the event of template is compromised, a new template can be generated by issuing a new set of random vectors from the user-specific token. Biohashing works in various biometric traits such as fingerprint minutia [9], fingerprint texture [16], face [10], iris [18] etc. However, the non-invertibility of the Biohashing could be jeopardized if both y and R are revealed.…”

mentioning

confidence: 99%

Ranking-Based Locality Sensitive Hashing-Enabled Cancelable Biometrics: Index-of-Max Hashing

Jin

Hwang

Lai

et al. 2018

IEEE Trans.Inform.Forensic Secur.

184

101

View full text Add to dashboard Cite

Abstract-In this paper, we propose a ranking based locality sensitive hashing inspired two-factor cancelable biometrics, dubbed "Index-of-Max" (IoM) hashing for biometric template protection. With externally generated random parameters, IoM hashing transforms a real-valued biometric feature vector into discrete index (max ranked) hashed code. We demonstrate two realizations from IoM hashing notion, namely Gaussian Random Projection based and Uniformly Random Permutation based hashing schemes. The discrete indices representation nature of IoM hashed codes enjoy several merits. Firstly, IoM hashing empowers strong concealment to the biometric information. This contributes to the solid ground of non-invertibility guarantee. Secondly, IoM hashing is insensitive to the features magnitude, hence is more robust against biometric features variation. Thirdly, the magnitude-independence trait of IoM hashing makes the hash codes being scale-invariant, which is critical for matching and feature alignment. The experimental results demonstrate favorable accuracy performance on benchmark FVC2002 and FVC2004 fingerprint databases. The analyses justify its resilience to the existing and newly introduced security and privacy attacks as well as satisfy the revocability and unlinkability criteria of cancelable biometrics.Index Terms-Fingerprint, cancelable template, Index-of-Max hashing, security and privacy I. INTRODUCTIONATELY, rapid proliferation of biometric applications leads to massive amount of biometric templates. Public worries about the security and privacy of the biometric templates if stolen or compromised. Such concerns are attributed to the strong binding of individuals and privacy, and further complicated by the fact that biometric traits are irrevocable. Given the above threats, a number of proposals have been reported to protect the biometric templates. Generally, the proposals available in the literature can be broadly divided into two categories: feature transformation (or cancelable biometrics) and biometric cryptosystems (biometric encryption). Biometric cryptosystem serves the purpose of either securing the secret using biometric feature (key binding) or generating the secret directly from the biometric feature (key generation). On the other hand, cancelable biometrics [1] is truly meant for biometric template protection. It refers to the irreversible transform that can alter the biometric templates such that security and privacy of the templates can be assured. If a cancelable template is compromised, a new template can be re-generated from the same biometrics.The cancelable biometric schemes in the literature vary according to different biometric modalities. However, the operation of a general cancelable biometrics system is similar to the conventional biometric system where the system composes of sensor, feature extractor and matcher except the former includes a parameterized transformation function right after feature extractor, and the matching is done in the transformed domain, rather in the feature doma...

show abstract

“…(see Note 1 and 2 for more discussion) 13. (optional to PLB) protected biometric feature with public parameters (PTB pub ): biometric feature in a protected form and generated with public parameters, e.g., fuzzy commitment [25], dynamic random projection [26], etc. 14.…”

Section: Digital Security Featuresmentioning

confidence: 99%

Towards standardizing trusted evidence of identity

Yang

Busch

Bringer³

et al. 2013

Proceedings of the 2013 ACM Workshop on Digital Identity Management

Self Cite

View full text Add to dashboard Cite

Evidence of identity (EOI), sometimes mentioned as breeder documents in a physical representation form, refers to a single or a set of evidence that can be used to provide confidence to the claimed identity. Trust of evidence of identity needs prudential assessment by an authority or a service provider before such evidence of identity can be accepted for identity verification or eligibility evaluation purposes. This is especially the case when such purposes have a high risk of cost, security, and other critical consequences. In this paper we analyze the status of deployed EOIs in the scope of ePassport issuance; and then attempt to define the implementation types, fraud scenarios, security objectives, and trust levels for EOIs, which have not been clearly defined in existing research and standardization societies. As a pilot survey work in this field, recommendations from policy and technology perspectives towards a highly-trusted EOI framework for standardization are shaped towards future ePassport issuance standardization and practice. Finally, a new design of birth certificate, compliant to the proposed recommendations, is presented as an example of trusted EOI.

show abstract

Dynamic random projection for biometric template protection

Cited by 87 publications

References 12 publications

Protected Honey Face Templates

Protected Honey Face Templates

Ranking-Based Locality Sensitive Hashing-Enabled Cancelable Biometrics: Index-of-Max Hashing

Towards standardizing trusted evidence of identity

Contact Info

Product

Resources

About