Identity by Design, Demographics by Accident: Demographic Leakage and Suppression in Behavioral Biometric Embeddings

• URL: http://arxiv.org/abs/2608.28921v1
• Date: Fri, 28 Aug 2026 22:41:06 GMT
• Title: Identity by Design, Demographics by Accident: Demographic Leakage and Suppression in Behavioral Biometric Embeddings
• Abstract summary: Behavioral biometric authentication (BBA) systems use deep learning models to transform biometric signals into identity embeddings for user authentication.<n>While designed to encode identity, these embeddings may inadvertently reveal sensitive demographic attributes, including gender, age, and height.<n>We present the first systematic audit of demographic leakage in BBA systems, evaluating 11 models across 9 datasets spanning four biometric modalities.
• Score: 0.8564059718893797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Behavioral biometric authentication (BBA) systems use deep learning models to transform biometric signals, such as eye movements, voice, keystroke/touchstroke dynamics, and gait, into identity embeddings for user authentication. While designed to encode identity, these embeddings may inadvertently reveal sensitive demographic attributes, including gender, age, and height. Consequently, an adversary with access to the authentication model can infer demographic information from biometric signals, including those of users unseen during training or enrollment. In this paper, we present the first systematic audit of demographic leakage in BBA systems, evaluating 11 models across 9 datasets spanning four biometric modalities. We further benchmark four post-hoc suppression methods-Incremental Variable Elimination (IVE), Hilbert-Schmidt Independence Criterion (HSIC), Adversarial Encoder-Decoder (AED), and Protected Attribute Suppression System (PASS) to assess their ability to mitigate demographic leakage while preserving authentication utility. Our analysis reveals substantial variation in leakage and suppressibility across modalities, model architectures, and learning objectives. While voice embeddings exhibit high leakage that can be effectively suppressed, keystroke/touchstroke embeddings exhibit lower leakage but are considerably more difficult to sanitize. These findings highlight a fundamental privacy risk in behavioral biometric authentication and provide insights into the factors governing demographic information suppressibility.

Related papers

• Adversarial Vulnerabilities of Neural Biomarker Identification Systems [0.0]
  We develop a collection of adaptive attack algorithms which learn to fool an authentication system via targeted alterations of stolen EEG recordings.<n>We show that vulnerability to spoofing attack is greatly impacted by the recording conditions, with significant variation depending on task at time of recording.
  arXiv  Detail & Related papers  (2026-09-01T20:39:51Z)
• Scalable Secure Biometric Authentication without Auxiliary Identifiers [54.032594016239926]
  We present a new biometric authentication system that provides provable security guarantees against data breaches.<n>Our work is the first to show that real-world scalable privacy-preserving biometric authentication without auxiliary identifiers is feasible.
  arXiv  Detail & Related papers  (2026-04-27T23:55:09Z)
• QUACK! Making the (Rubber) Ducky Talk: A Systematic Study of Keystroke Dynamics for HID Injection Detection [60.105690843777666]
  We show that robust, privacy-preserving detection is achievable using lightweight models operating solely on timing features.<n>Our analysis reveals that attacker sophistication does not monotonically translate into improved evasion.
  arXiv  Detail & Related papers  (2026-04-17T08:53:24Z)
• Detecting Cognitive Signatures in Typing Behavior for Non-Intrusive Authorship Verification [0.0]
  The proliferation of AI-generated text has intensified the need for reliable authorship verification, yet current output-based methods are increasingly unreliable.<n>We observe that the ordinary typing interface captures rich cognitive signatures, measurable patterns in keystroke timing that reflect the planning, translating, and revising stages of genuine composition.<n>We present a non-intrusive verification framework that operates within existing writing interfaces, collecting only timing metadata to preserve privacy.
  arXiv  Detail & Related papers  (2026-02-26T20:02:55Z)
• Deep Learning Models for Robust Facial Liveness Detection [56.08694048252482]
  This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques.<n>By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision.
  arXiv  Detail & Related papers  (2025-08-12T17:19:20Z)
• A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage [77.83757117924995]
  We propose a new framework that evaluates re-identification attacks to quantify individual privacy risks upon data release.<n>Our approach shows that seemingly innocuous auxiliary information can be used to infer sensitive attributes like age or substance use history from sanitized data.
  arXiv  Detail & Related papers  (2025-04-28T01:16:27Z)
• Support Vector Machine for Person Classification Using the EEG Signals [0.4419843514606336]
  We propose using Electroencephalogram (EEG) signals for individual identification to address this challenge. EEG signals offer promising authentication potential and provide a novel means for liveness detection, thereby mitigating spoofing attacks. This study employs a public dataset initially compiled for fatigue analysis, featuring EEG data from 12 subjects recorded via an eight-channel OpenBCI helmet.
  arXiv  Detail & Related papers  (2024-11-26T14:03:58Z)
• Model-Agnostic Utility-Preserving Biometric Information Anonymization [9.413512346732768]
  The recent rapid advancements in both sensing and machine learning technologies have given rise to the universal collection and utilization of people's biometrics. The use of biometrics has raised serious privacy concerns due to their intrinsic sensitive nature and the accompanying high risk of leaking sensitive information. We propose a novel modality-agnostic data transformation framework that is capable of anonymizing biometric data by suppressing its sensitive attributes and retaining features relevant to downstream machine learning-based analyses.
  arXiv  Detail & Related papers  (2024-05-23T21:21:40Z)
• Biometrics Employing Neural Network [0.0]
  Fingerprints, iris and retina patterns, facial recognition, hand shapes, palm prints, and voice recognition are frequently used forms of biometrics. For systems to be effective and widely accepted, the error rate in recognition and verification must approach zero. Artificial Neural Networks, which simulate the human brain's operations, present themselves as a promising approach.
  arXiv  Detail & Related papers  (2024-02-01T03:59:04Z)
• Privacy-preserving Multi-biometric Indexing based on Frequent Binary Patterns [7.092869001331781]
  We propose an efficient privacy-preserving multi-biometric identification system that retrieves protected deep cancelable templates. A multi-biometric binning scheme is designed to exploit the low intra-class variation properties contained in the frequent binary patterns extracted from different types of biometric characteristics.
  arXiv  Detail & Related papers  (2023-10-04T18:18:24Z)
• PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition [55.858374644761525]
  Face recognition networks encode information about sensitive attributes while being trained for identity classification. Existing bias mitigation approaches require end-to-end training and are unable to achieve high verification accuracy. We present a descriptors-based adversarial de-biasing approach called Protected Attribute Suppression System ( PASS)' Pass can be trained on top of descriptors obtained from any previously trained high-performing network to classify identities and simultaneously reduce encoding of sensitive attributes.
  arXiv  Detail & Related papers  (2021-08-09T00:39:22Z)
• Biometrics: Trust, but Verify [49.9641823975828]
  Biometric recognition has exploded into a plethora of different applications around the globe. There are a number of outstanding problems and concerns pertaining to the various sub-modules of biometric recognition systems.
  arXiv  Detail & Related papers  (2021-05-14T03:07:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.