Multi-Level Privacy-Preserving Dementia Detection from Speech via Targeted Adversarial Obfuscation and Representation Learning

• URL: http://arxiv.org/abs/2607.17098v1
• Date: Sun, 19 Jul 2026 06:48:54 GMT
• Title: Multi-Level Privacy-Preserving Dementia Detection from Speech via Targeted Adversarial Obfuscation and Representation Learning
• Abstract summary: Speech recordings used for dementia detection expose speaker identity, raising critical privacy concerns.<n>We propose a multi-level framework designed to neutralize two distinct eavesdropping vectors.<n>At the signal level, a Cumulative Signal Attack concentrates perturbations in keyword-aligned regions to maximize transcription error.<n>At the feature level, a Gradient Reversal Layer (GRL) with Mutual Information (MI)-guided noise injection suppresses speaker-discriminative dimensions.
• Score: 2.4214594180459366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Speech recordings used for dementia detection inherently expose speaker identity, raising critical privacy concerns. Existing methods typically address only singular threats and fail to resolve the privacy--utility trade-off. We propose a multi-level framework designed to neutralize two distinct eavesdropping vectors. At the signal level, a Cumulative Signal Attack (CSA) concentrates perturbations in keyword-aligned regions to maximize transcription error (Word Error Rate WER = 1.00) while preserving vital prosodic biomarkers. At the feature level, a Gradient Reversal Layer (GRL) with Mutual Information (MI)-guided noise injection suppresses speaker-discriminative dimensions while retaining dementia-relevant diagnostic structure. Evaluated on the DementiaBank Pitt Corpus, our framework achieves near-chance speaker identification (Equal Error Rate EER = 0.59, F1 = 0.003) while maintaining strong dementia classification performance (F1 = 0.78, AUC = 0.86).

Related papers

• CCMAN: Cognitive Instability-Aware Cross-Modal Attention Network for Interpretable Temporal Biomarkers of Verbal Fluency Speech [7.12685963584208]
  Early detection of cognitive decline from speech offers a scalable and non-invasive alternative to conventional clinical assessment.<n>We propose the Cognitive Instability-Aware Cross-Modal Attention Network (CCMAN), a transfer learning framework that learns task-agnostic cognitive speech representations.<n>Experiments were conducted on 165.44 hours of speech from 843 participants.
  arXiv  Detail & Related papers  (2026-09-13T19:55:08Z)
• Transcript-Free Lightweight Detection of Alzheimer's Disease from Spontaneous Speech Using Handcrafted MFCC-Dominant Acoustic Biomarkers [7.901493394283502]
  It is still hard to find Alzheimer's disease (AD) early, especially when neuroimaging is expensive or tools that depend on language are not available.<n>We offer a simple, audio-only baseline for detecting AD using 176 Cookie Theft recordings from the DementiaBank corpus.<n>We take out 99 hand-crafted acoustic-temporal features, including pause and statistics, spectral/prosodic descriptors, and fluency summaries and .
  arXiv  Detail & Related papers  (2026-07-11T07:19:16Z)
• Towards Personalized Federated Learning for Dysarthric Speech Recognition [49.291957451546914]
  This paper explores two aggregation strategies to achieve personalization, including the parameter-based averaging strategy and the embedding-based averaging strategy.<n> Experiments on UASpeech and TORGO show that the proposed methods outperform the baseline regularized FedAvg by statistically significant WER reductions of up to 0.99% absolute (3.15% relative) on UASpeech and 0.56% absolute (4.73% relative) on TORGO, respectively.
  arXiv  Detail & Related papers  (2026-06-11T12:10:57Z)
• National Institute on Aging PREPARE Challenge: Early Detection of Cognitive Impairment Using Speech -- The SpeechCARE Solution [1.0486773259892048]
  Alzheimer's disease and related dementias affect one in five adults over 60, yet more than half of individuals with cognitive decline remain undiagnosed.<n>SpeechCARE is a multimodal speech processing pipeline that captures subtle speech-related cues associated with cognitive impairment.<n>Its robust preprocessing includes automatic transcription, large language model (LLM)-based anomaly detection, and task identification.
  arXiv  Detail & Related papers  (2025-11-11T11:39:20Z)
• Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment [48.73836179661632]
  Confidence-guided adversarial alignment adaptively suppresses attack-specific artifacts without erasing discriminative cues.<n>IB-CAAN consistently outperforms baseline and state-of-the-art performance on many benchmarks.
  arXiv  Detail & Related papers  (2025-09-28T03:48:49Z)
• VoxGuard: Evaluating User and Attribute Privacy in Speech via Membership Inference Attacks [51.68795949691009]
  We introduce VoxGuard, a framework grounded in differential privacy and membership inference.<n>For attributes, we show that simple transparent attacks recover gender and accent with near-perfect accuracy even after anonymization.<n>Our results demonstrate that EER substantially underestimates leakage, highlighting the need for low-FPR evaluation.
  arXiv  Detail & Related papers  (2025-09-22T20:57:48Z)
• Prosody-Driven Privacy-Preserving Dementia Detection [3.9530780161144667]
  We aim to anonymize embeddings while preserving the diagnostic utility for dementia detection. We propose a novel approach that leverages domain knowledge to disentangle prosody features relevant to dementia from speaker embeddings.
  arXiv  Detail & Related papers  (2024-07-03T19:34:47Z)
• Automatically measuring speech fluency in people with aphasia: first achievements using read-speech data [55.84746218227712]
  This study aims at assessing the relevance of a signalprocessingalgorithm, initially developed in the field of language acquisition, for the automatic measurement of speech fluency.
  arXiv  Detail & Related papers  (2023-08-09T07:51:40Z)
• The effect of speech pathology on automatic speaker verification -- a large-scale study [6.468412158245622]
  pathological speech faces heightened privacy breach risks compared to healthy speech. Adults with dysphonia are at heightened re-identification risks, whereas conditions like dysarthria yield results comparable to those of healthy speakers. Merging data across pathological types led to a marked EER decrease, suggesting the potential benefits of pathological diversity in automatic speaker verification.
  arXiv  Detail & Related papers  (2022-04-13T15:17:00Z)
• Investigation of Data Augmentation Techniques for Disordered Speech Recognition [69.50670302435174]
  This paper investigates a set of data augmentation techniques for disordered speech recognition. Both normal and disordered speech were exploited in the augmentation process. The final speaker adapted system constructed using the UASpeech corpus and the best augmentation approach based on speed perturbation produced up to 2.92% absolute word error rate (WER)
  arXiv  Detail & Related papers  (2022-01-14T17:09:22Z)
• Class-Conditional Defense GAN Against End-to-End Speech Attacks [82.21746840893658]
  We propose a novel approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. Unlike conventional defense approaches, the proposed approach does not directly employ low-level transformations such as autoencoding a given input signal. Our defense-GAN considerably outperforms conventional defense algorithms in terms of word error rate and sentence level recognition accuracy.
  arXiv  Detail & Related papers  (2020-10-22T00:02:02Z)

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.