Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition With Privacy Protection

Drozdowski, Pawel; Stockhardt, Fabian; Rathgeb, Christian; Osorio-Roig, Daile; Busch, Christoph

doi:10.1109/access.2021.3118830

Cited by 18 publications

(14 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the computational overhead of such a scheme is expected to be high, we show how it can be reduced to a feasible amount without compromising the security of the system. The only other work comparable work is [14], which achieves provable security by homomorphic encryption and preselection by feature fusion. However, it requires significantly more memory than our proposed approach, and is limited in terms of penetration rate.…”

Section: Search Space Reduction Provable Security Scalabilitymentioning

confidence: 99%

“…However, it requires significantly more memory than our proposed approach, and is limited in terms of penetration rate. When a reference is added to the database in [14], the entire system needs to setup anew, introducing considerable complexity that is omitted in our approach. Taking into account these differences, our approach overall more efficient and flexible.…”

Section: Search Space Reduction Provable Security Scalabilitymentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Preserving Preselection for Protected Biometric Identification Using Public-Key Encryption With Keyword Search

Bauspie

Kolberg

Drozdowski³

et al. 2023

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

The efficiency of biometric systems, in particular efficient and accurate biometric identification, is one of the most challenging open problems in biometrics today. Adding to that, biometric data are sensitive data deserving adequate protection. As a solution, this work proposes an efficient privacy-preserving reduction of the computational workload of biometric identification systems using public-key encryption with keyword search (PEKS). For long-term protection of the biometric data, fully homomorphic encryption is applied for template protection. As all applied cryptographic schemes are lattice-based, they also offer post-quantum security. Throughout the system, the recognition accuracy of the unprotected system is preserved. In an evaluation on a public face database, the computational workload of an identification search in the encrypted domain is reduced down to 8.4% compared to an exhaustive search, achieving identification on 1062 subjects in 210 milliseconds. Based on these results, an identification search on 1 million subjects can be estimated at under 3 minutes using off-the-shelf hardware.

show abstract

Section: Search Space Reduction Provable Security Scalabilitymentioning

confidence: 99%

Section: Search Space Reduction Provable Security Scalabilitymentioning

confidence: 99%

Privacy-Preserving Preselection for Protected Biometric Identification Using Public-Key Encryption With Keyword Search

Bauspie

Kolberg

Drozdowski³

et al. 2023

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Drozdowski et al [ 63 ] reduced the computational overheads associated with face recognition transactions without dropping recognition performance. Through the seamless integration of template protection with open-source HE libraries, the proposed method guaranteed the irreversibility, unlinkability and renewability of the protected biometric data.…”

Section: He-based Approaches To Biometric Securitymentioning

confidence: 99%

A Review of Homomorphic Encryption for Privacy-Preserving Biometrics

Yang

Wang

Cui

et al. 2023

Sensors

View full text Add to dashboard Cite

The advancement of biometric technology has facilitated wide applications of biometrics in law enforcement, border control, healthcare and financial identification and verification. Given the peculiarity of biometric features (e.g., unchangeability, permanence and uniqueness), the security of biometric data is a key area of research. Security and privacy are vital to enacting integrity, reliability and availability in biometric-related applications. Homomorphic encryption (HE) is concerned with data manipulation in the cryptographic domain, thus addressing the security and privacy issues faced by biometrics. This survey provides a comprehensive review of state-of-the-art HE research in the context of biometrics. Detailed analyses and discussions are conducted on various HE approaches to biometric security according to the categories of different biometric traits. Moreover, this review presents the perspective of integrating HE with other emerging technologies (e.g., machine/deep learning and blockchain) for biometric security. Finally, based on the latest development of HE in biometrics, challenges and future research directions are put forward.

show abstract

“…Engelsma et al [18] proposed an efficient way to search encrypted templates by combining a novel encoding scheme with feature compression. By using a tree search structure created by fusing similar templates, Drozdowski et al [16] developed a method for faster biometric indexing and retrieval. In contrast to this body of work, in this paper, we leverage fully homomorphic encryption for end-to-end template fusion and match score computation and devise an FHE-aware learning algorithm for feature projection.…”

Section: Related Workmentioning

confidence: 99%

“…AUROC comparison of HEFT versus baselines introduced in[16]. Table2compares the performance of HEFT with the baselines.…”

mentioning

confidence: 99%

HEFT: Homomorphically Encrypted Fusion of Biometric Templates

Sperling¹,

Ratha²,

Ross³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper proposes a non-interactive end-to-end solution for secure fusion and matching of biometric templates using fully homomorphic encryption (FHE). Given a pair of encrypted feature vectors, we perform the following ciphertext operations, i) feature concatenation, ii) fusion and dimensionality reduction through a learned linear projection, iii) scale normalization to unit 2 -norm, and iv) match score computation. Our method, dubbed HEFT (Homomorphically Encrypted Fusion of biometric Templates), is customdesigned to overcome the unique constraint imposed by FHE, namely the lack of support for non-arithmetic operations. From an inference perspective, we systematically explore different data packing schemes for computationally efficient linear projection and introduce a polynomial approximation for scale normalization. From a training perspective, we introduce an FHE-aware algorithm for learning the linear projection matrix to mitigate errors induced by approximate normalization. Experimental evaluation for template fusion and matching of face and voice biometrics shows that HEFT (i) improves biometric verification performance by 11.07% and 9.58% AUROC compared to the respective unibiometric representations while compressing the feature vectors by a factor of 16 (512D to 32D), and (ii) fuses a pair of encrypted feature vectors and computes its match score against a gallery of size 1024 in 884 ms. Code and data are available at https://github.com/humananalysis/encrypted-biometric-fusion

show abstract

Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition With Privacy Protection

Cited by 18 publications

References 68 publications

Privacy-Preserving Preselection for Protected Biometric Identification Using Public-Key Encryption With Keyword Search

Privacy-Preserving Preselection for Protected Biometric Identification Using Public-Key Encryption With Keyword Search

A Review of Homomorphic Encryption for Privacy-Preserving Biometrics

HEFT: Homomorphically Encrypted Fusion of Biometric Templates

Contact Info

Product

Resources

About