# Beyond Identity: What Information Is Stored in Biometric Face Templates?

arXiv: https://arxiv.org/abs/2009.09918 · HTML: https://mlsanity.com/paper/2009.09918/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 23 of 23)

- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition](https://mlsanity.com/paper/2108.03764/) (2021)
- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [An Overview of Privacy-enhancing Technologies in Biometric Recognition](https://mlsanity.com/paper/2206.10465/) (2022)
- [Towards Protecting Face Embeddings in Mobile Face Verification Scenarios](https://mlsanity.com/paper/2110.00434/) (2021)
- [Analyzing Fairness in Deepfake Detection With Massively Annotated Databases](https://mlsanity.com/paper/2208.05845/) (2022)
- [Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques](https://mlsanity.com/paper/2110.05044/) (2021)
- [Causality-Inspired Taxonomy for Explainable Artificial Intelligence](https://mlsanity.com/paper/2208.09500/) (2022)
- [On the (Limited) Generalization of MasterFace Attacks and Its Relation to the Capacity of Face Representations](https://mlsanity.com/paper/2203.12387/) (2022)
- [Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention](https://mlsanity.com/paper/2304.02284/) (2023)
- [An Attack on Facial Soft-biometric Privacy Enhancement](https://mlsanity.com/paper/2111.12405/) (2021)
- [Dissecting Human Body Representations in Deep Networks Trained for Person Identification](https://mlsanity.com/paper/2502.15934/) (2025)
- [Massively Annotated Datasets for Assessment of Synthetic and Real Data in Face Recognition](https://mlsanity.com/paper/2404.15234/) (2024)
- [On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes](https://mlsanity.com/paper/2501.12020/) (2025)
- [A Deeper Dive into the Irreversibility of PolyProtect: Making Protected Face Templates Harder to Invert](https://mlsanity.com/paper/2605.03857/) (2026)
- [Generalizability and Application of the Skin Reflectance Estimate Based on Dichromatic Separation (SREDS)](https://mlsanity.com/paper/2309.01235/) (2023)
- [A Responsible Face Recognition Approach for Small and Mid-Scale Systems Through Personalized Neural Networks](https://mlsanity.com/paper/2505.19920/) (2025)
- [Realistic Face Reconstruction from Facial Embeddings via Diffusion Models](https://mlsanity.com/paper/2602.13168/) (2026)
- [Variational Latent Entropy Estimation Disentanglement: Controlled Attribute Leakage for Face Recognition](https://mlsanity.com/paper/2604.11250/) (2026)
- [Bias Mitigation in Face Recognition via Demographic-based Supervised Contrastive Learning](https://mlsanity.com/paper/2608.12971/) (2026)
- [SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates](https://mlsanity.com/paper/2608.16251/) (2026)
- [Unmasking Face Embeddings: Reading, Rendering and Naming with Foundation Models](https://mlsanity.com/paper/2609.00411/) (2026)
- [Is it Possible to Generate Irreversible PolyProtected Templates from Face Embeddings using System-Specific Keys?](https://mlsanity.com/paper/2610.01385/) (2026)

## Abstract (arXiv)

Deeply-learned face representations enable the success of current face recognition systems. Despite the ability of these representations to encode the identity of an individual, recent works have shown that more information is stored within, such as demographics, image characteristics, and social traits. This threatens the user's privacy, since for many applications these templates are expected to be solely used for recognition purposes. Knowing the encoded information in face templates helps to develop bias-mitigating and privacy-preserving face recognition technologies. This work aims to support the development of these two branches by analysing face templates regarding 113 attributes. Experiments were conducted on two publicly available face embeddings. For evaluating the predictability of the attributes, we trained a massive attribute classifier that is additionally able to accurately state its prediction confidence. This allows us to make more sophisticated statements about the attribute predictability. The results demonstrate that up to 74 attributes can be accurately predicted from face templates. Especially non-permanent attributes, such as age, hairstyles, haircolors, beards, and various accessories, found to be easily-predictable. Since face recognition systems aim to be robust against these variations, future research might build on this work to develop more understandable privacy preserving solutions and build robust and fair face templates.