IDFace: Face Template Protection for Efficient and Secure Identification
Not on the map. Why?
Abstract (arXiv)
As face recognition systems (FRS) become more widely used, user privacy becomes more important. A key privacy issue in FRS is protecting the user's face template, as the characteristics of the user's face image can be recovered from the template. Although recent advances in cryptographic tools such as homomorphic encryption (HE) have provided opportunities for securing the FRS, HE cannot be used directly with FRS in an efficient plug-and-play manner. In particular, although HE is functionally complete for arbitrary programs, it is basically designed for algebraic operations on encrypted data of predetermined shape, such as a polynomial ring. Thus, a non-tailored combination of HE and the system can yield very inefficient performance, and many previous HE-based face template protection methods are hundreds of times slower than plain systems without protection. In this study, we propose IDFace, a new HE-based secure and efficient face identification method with template protection. IDFace is designed on the basis of two novel techniques for efficient searching on a (homomorphically encrypted) biometric database with an angular metric. The first technique is a template representation transformation that sharply reduces the unit cost for the matching test. The second is a space-efficient encoding that reduces wasted space from the encryption algorithm, thus saving the number of operations on encrypted templates. Through experiments, we show that IDFace can identify a face template from among a database of 1M encrypted templates in 126ms, showing only 2X overhead compared to the identification over plaintexts.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 109 references that are in the map. First posted on arXiv 16 Jul 2025.
Builds on
36 of 109 references.
References · 36
- 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
- 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
- 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 334
- 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 308
- 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 223
- 2016Trained Ternary Quantizationcited by 208
- 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 144
- 2017On the Reconstruction of Face Images from Deep Face Templatescited by 67
- 2022Pushing the limits of raw waveform speaker recognitioncited by 51
- 2019Learning a Fixed-Length Fingerprint Representationcited by 49
- 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
- 2024KeyPoint Relative Position Encoding for Face Recognitioncited by 38
24 more
- 2020Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognitioncited by 36
- 2018Secure Face Matching Using Fully Homomorphic Encryptioncited by 29
- 2024Reshape Dimensions Network for Speaker Recognitioncited by 28
- 2020HERS: Homomorphically Encrypted Representation Searchcited by 26
- 2023Privacy-preserving Adversarial Facial Featurescited by 24
- 2024Privacy-Preserving Face Recognition Using Trainable Feature Subtractioncited by 24
- 2023Controllable Inversion of Black-Box Face Recognition Models via Diffusioncited by 22
- 2017Ranking Based Locality Sensitive Hashing Enabled Cancelable Biometrics: Index-of-Max Hashingcited by 21
- 2023Privacy-Preserving Face Recognition Using Random Frequency Componentscited by 15
- 2023UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognitioncited by 10
- 2019Zero-Shot Deep Hashing and Neural Network Based Error Correction for Face Template Protectioncited by 9
- 2019A Cryptanalysis of Two Cancelable Biometric Schemes based on Index-of-Max Hashingcited by 9
- 2021IronMask: Modular Architecture for Protecting Deep Face Templatecited by 9
- 2024Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Modelcited by 9
- 2023Benchmarking fixed-length Fingerprint Representations across different Embedding Sizes and Sensor Typescited by 8
- 2020Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attackcited by 6
- 2021Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition with Privacy Protectioncited by 5
- 2023Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authenticationcited by 3
- 2024Face Reconstruction Transfer Attack as Out-of-Distribution Generalizationcited by 3
- 2022Assessing Privacy Risks from Feature Vector Reconstruction Attackscited by 2
- 2022Towards Privacy-Preserving, Real-Time and Lossless Feature Matchingcited by 2
- 2024Blind-Match: Efficient Homomorphic Encryption-Based 1:N Matching for Privacy-Preserving Biometric Identificationcited by 2
- 2024MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveformscited by 1
- 2024WiFaKey: Generating Cryptographic Keys from Face in the Wildcited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.