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

TL;DR

This paper analyzes what information, including demographic and social traits, is stored in deep face templates, revealing that many attributes can be accurately predicted, raising privacy concerns.

Contribution

It provides a comprehensive analysis of 113 attributes stored in face templates, highlighting the extent of information leakage and its implications for privacy and fairness.

Findings

Up to 74 attributes can be accurately predicted from face templates.

Non-permanent attributes like age and hairstyle are especially predictable.

The attribute classifier also estimates prediction confidence for better analysis.

Abstract

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.