Significant Feature Based Representation for Template Protection

Mohan, Deen Dayal; Sankaran, Nishant; Tulyakov, Sergey; Setlur, Srirangaraj; Govindaraju, Venu

doi:10.1109/cvprw.2019.00293

Cited by 14 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods use some sort of algorithmically defined transformation to convert the face embeddings (learned from the input face images) to more secure representations. The proposed transformations include one-way cryptographic [6] or Winner Takes All [7] hashing, convolution of the embedding with a random kernel [8], use of the Fuzzy Commitment [9] or Fuzzy Vault [10] scheme, fusion of a subject's face embedding with a different subject's face embedding using keys extracted from the two sets of features [11], and homomorphic encryption [12]. The main issue with these approaches is that they have not been comprehensively evaluated in terms of their ability to simultaneously satisfy all three properties of face embedding protection methods.…”

Section: Face Embedding Protection Methodsmentioning

confidence: 99%

“…In the worst-case (SCE) scenario where all users' parameters are stolen, the recognition accuracy of a PolyProtected system may be worse than that of the baseline; however, our results indicate that the performance can be improved by tuning the amount of overlap used in the PolyProtect mapping as well as the FMR tolerance of the underlying system. So, although this worst-case scenario is highly unlikely to occur in practice 9 , even in this case the recognition accuracy should be acceptable, ensuring that the system does not suffer much in the time it takes to replace the compromised PolyProtected template(s). We may thus reasonably conclude that PolyProtect is capable of satisfying the recognition accuracy property of a face embedding protection scheme.…”

Section: Recognition Accuracymentioning

confidence: 99%

See 1 more Smart Citation

Towards Protecting Face Embeddings in Mobile Face Verification Scenarios

Hahn,

Marcel

2021

Preprint

View full text Add to dashboard Cite

This paper proposes PolyProtect, a method for protecting the sensitive face embeddings that are used to represent people's faces in neural-network-based face verification systems. PolyProtect transforms a face embedding to a more secure template, using a mapping based on multivariate polynomials parameterised by user-specific coefficients and exponents. In this work, PolyProtect is evaluated on two open-source face verification systems in a mobile application context, under the toughest threat model that assumes a fully-informed attacker with complete knowledge of the system and all its parameters. Results indicate that PolyProtect can be tuned to achieve a satisfactory trade-off between the recognition accuracy of the PolyProtected face verification system and the irreversibility of the PolyProtected templates. Furthermore, PolyProtected templates are shown to be effectively unlinkable, especially if the user-specific parameters employed in the PolyProtect mapping are selected in a non-naive manner. The evaluation is conducted using practical methodologies with tangible results, to present realistic insight into the method's robustness as a face embedding protection scheme in practice. The code to fully reproduce this work is available at: https://gitlab.idiap.ch/bob/bob.paper.polyprotect 2021.

show abstract

Section: Face Embedding Protection Methodsmentioning

confidence: 99%

Section: Recognition Accuracymentioning

confidence: 99%

Towards Protecting Face Embeddings in Mobile Face Verification Scenarios

Hahn,

Marcel

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In this case, an appropriate error-correction mechanism should be able to correct a sufficient number of errors in the recovered codeword, such that the hash of the corrected codeword matches the hash of the reference codeword. Variants of the Fuzzy Commitment scheme were investigated for the protection of NN-extracted face features in [14]- [16].…”

Section: A Non-nn Face Btp Methodsmentioning

confidence: 99%

“…The first reason was to train a reliable NN-based feature extractor (by either fine-tuning an adopted/modified DNN model/architecture, or by training a proprietary DNN), so that a handcrafted BTP algorithm could be applied to the extracted face features. This approach was used in [6], [13], [14], [18], [19]. Similarly, [11] trained a DNN to reduce a face feature vector to its "intrinsic" dimensionality before encrypting it (via HE), while [21] and [30] trained a CNN and an SVM, respectively, to classify already-protected face templates.…”

Section: A Reproducibilitymentioning

confidence: 99%

Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques

Hahn¹,

Marcel²

2021

Preprint

View full text Add to dashboard Cite

As automated face recognition applications tend towards ubiquity, there is a growing need to secure the sensitive face data used within these systems. This paper presents a survey of biometric template protection (BTP) methods proposed for securing face "templates" (images or representative features) in neural-network-based face recognition systems. The BTP methods are categorised into two types: Non-NN and NN-learned. Non-NN methods use a neural network (NN) as a feature extractor, but the BTP part is based on a non-NN algorithm applied at either image-level or feature-level. In contrast, NN-learned methods specifically employ a NN to learn a protected template from the unprotected face image or features. We present examples of Non-NN and NN-learned face BTP methods from the literature, along with a discussion of the two categories' comparative strengths and weaknesses. We also investigate the techniques used to evaluate these BTP methods, in terms of the three most common BTP criteria: "recognition accuracy", "irreversibility", and "renewability/unlinkability". As expected, the recognition accuracy of protected face recognition systems is generally evaluated using the same (empirical) techniques employed for evaluating standard (unprotected) biometric systems. On the contrary, most irreversibility and renewability/unlinkability evaluations are found to be based on theoretical assumptions/estimates or verbal implications, with a lack of empirical validation in a practical face recognition context. We recommend, therefore, a greater focus on empirical evaluation strategies, to provide more concrete insights into the irreversibility and renewability/unlinkability of face BTP methods in practice. Additionally, an exploration of the reproducibility of the studied BTP works, in terms of the public availability of their implementation code and evaluation datasets/procedures, suggests that it would currently be difficult for the BTP community to faithfully replicate (and thus validate) most of the reported findings. So, we advocate for a push towards reproducibility, in the hope of furthering our understanding of the face BTP research field.

show abstract

“…To address the advent of similarity-based attacks (SA), Deep Secure Quantization (DSQ) based on neural network implementations is used to protect iris feature [31]. Deen Dayal Mohan presented a significant bit based representation for creating secure face templates with negligible degradation in the performance [32]. Compared with single biometrics system, multi-biometrics system which integrates multiple biometrics can improve the accuracy and security of recognition.…”

Section: Related Workmentioning

confidence: 99%

One-Factor Cancellable Palmprint Recognition Scheme Based on OIOM and Minimum Signature Hash

Wang

2019

IEEE Access

View full text Add to dashboard Cite

The traditional Cancellable biometrics scheme needs another key or token to generate the revocable template, which usually suffers from the token-stolen problem. To solve this problem, a one-factor cancellable palmprint biometric recognition scheme based on Orthogonal Index of Maximum (OIOM) hash and Minimum Signature Hash (MSH) is proposed to generate pseudonymous identifier. Firstly, to improve the efficiency and effectiveness, a parallel structure is designed to obtain Orthogonal Gaussian random projection(GRP)matrices, which is employed to generate the OIOM hash code. Secondly, a random binary string is XOR the binary OIOM hash code to construct the helper data and it is stored in the database. Meanwhile, this string is hashed by MSH to get the final pseudonymous identifier. Lastly, during matching stage, based on helper data and a palmprint images, another pseudonymous identifier is generated to recognition. This implies that, just one factor, a palmprint of user, is needed in the matching stage, and therefore the privacy of user is preserved. To evaluate the proposed scheme, PolyU database and touchless TJU database are used in experiments. The noninvertible, renewability, unlinkability and several security attacks of the proposed scheme are analyzed. The experiment results and analysis show that the proposed scheme has strong security on the basis of maintaining palmprint recognition performance.INDEX TERMS Biometric recognition, cancellable palmprint feature, orthogonal index of maximum, minimum signature hash.

show abstract

Significant Feature Based Representation for Template Protection

Cited by 14 publications

References 31 publications

Towards Protecting Face Embeddings in Mobile Face Verification Scenarios

Towards Protecting Face Embeddings in Mobile Face Verification Scenarios

Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques

One-Factor Cancellable Palmprint Recognition Scheme Based on OIOM and Minimum Signature Hash

Contact Info

Product

Resources

About