# IDFace: Face Template Protection for Efficient and Secure Identification arXiv: https://arxiv.org/abs/2507.12050 ยท HTML: https://mlsanity.com/paper/2507.12050/ ## 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 (most cited first, 30 of 36) - [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016) - [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022) - [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021) - [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024) - [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021) - [Trained Ternary Quantization](https://mlsanity.com/paper/1612.01064/) (2016) - [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021) - [On the Reconstruction of Face Images from Deep Face Templates](https://mlsanity.com/paper/1703.00832/) (2017) - [Pushing the limits of raw waveform speaker recognition](https://mlsanity.com/paper/2203.08488/) (2022) - [Learning a Fixed-Length Fingerprint Representation](https://mlsanity.com/paper/1909.09901/) (2019) - [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021) - [KeyPoint Relative Position Encoding for Face Recognition](https://mlsanity.com/paper/2403.14852/) (2024) - [Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition](https://mlsanity.com/paper/2003.06958/) (2020) - [Secure Face Matching Using Fully Homomorphic Encryption](https://mlsanity.com/paper/1805.00577/) (2018) - [Reshape Dimensions Network for Speaker Recognition](https://mlsanity.com/paper/2407.18223/) (2024) - [HERS: Homomorphically Encrypted Representation Search](https://mlsanity.com/paper/2003.12197/) (2020) - [Privacy-preserving Adversarial Facial Features](https://mlsanity.com/paper/2305.05391/) (2023) - [Privacy-Preserving Face Recognition Using Trainable Feature Subtraction](https://mlsanity.com/paper/2403.12457/) (2024) - [Controllable Inversion of Black-Box Face Recognition Models via Diffusion](https://mlsanity.com/paper/2303.13006/) (2023) - [Ranking Based Locality Sensitive Hashing Enabled Cancelable Biometrics: Index-of-Max Hashing](https://mlsanity.com/paper/1703.05455/) (2017) - [Privacy-Preserving Face Recognition Using Random Frequency Components](https://mlsanity.com/paper/2308.10461/) (2023) - [UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition](https://mlsanity.com/paper/2311.02523/) (2023) - [Zero-Shot Deep Hashing and Neural Network Based Error Correction for Face Template Protection](https://mlsanity.com/paper/1908.02706/) (2019) - [A Cryptanalysis of Two Cancelable Biometric Schemes based on Index-of-Max Hashing](https://mlsanity.com/paper/1910.01389/) (2019) - [IronMask: Modular Architecture for Protecting Deep Face Template](https://mlsanity.com/paper/2104.02239/) (2021) - [Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Model](https://mlsanity.com/paper/2411.03960/) (2024) - [Benchmarking fixed-length Fingerprint Representations across different Embedding Sizes and Sensor Types](https://mlsanity.com/paper/2307.08615/) (2023) - [Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attack](https://mlsanity.com/paper/2006.13051/) (2020) - [Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition with Privacy Protection](https://mlsanity.com/paper/2107.12675/) (2021) - [Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication](https://mlsanity.com/paper/2312.11575/) (2023) ## Built on by (most cited first, 3 of 3) - [LocalScore: Local Density-Aware Similarity Scoring for Biometrics](https://mlsanity.com/paper/2602.01012/) (2026) - [SapiensID 2.0: Aligning Human Recognition Foundation Models with Human Perception](https://mlsanity.com/paper/2608.10497/) (2026) - [EventFace: Event-Based Face Recognition via Structure-Driven Spatiotemporal Modeling](https://mlsanity.com/paper/2604.06782/) (2026) ## 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.