paper-with-me

홈 › Papers

Personal Attribute Leakage in Federated Speech Models

2025-10-15 · Hamdan Al-Ali, Ali Reza Ghavamipour, Tommaso Caselli, Fatih Turkmen, Zeerak Talat, Hanan Aldarmaki arxiv

Federated learning is a common method for privacy-preserving training of machine learning models. In this paper, we analyze the vulnerability of ASR models to attribute inference attacks in the federated setting. We test a non-parametric white-box attack method under a passive threat model on three ASR models: Wav2Vec2, HuBERT, and Whisper. The attack operates solely on weight differentials without access to raw speech from target speakers. We demonstrate attack feasibility on sensitive demographic and clinical attributes: gender, age, accent, emotion, and dysarthria. Our findings indicate that attributes that are underrepresented or absent in the pre-training data are more vulnerable to such inference attacks. In particular, information about accents can be reliably inferred from all models. Our findings expose previously undocumented vulnerabilities in federated ASR models and offer insights towards improved security.

📄 PDF Abstract BibTeX arXiv:2510.13357

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

User Consented Federated Recommender System Against Personalized Attribute Inference Attack

2023-12-23 · Qi Hu, Yangqiu Song

Recommender systems can be privacy-sensitive. To protect users' private historical interactions, federated learning has been proposed in distributed learning for user representations. Using federated recommender (FedRec)…

AttributeFederated LearningInference AttackRecommendation Systems

Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings

2021-12-26 · Tiantian Feng, Hanieh Hashemi, Rajat Hebbar, Murali Annavaram 외

Speech emotion recognition (SER) processes speech signals to detect and characterize expressed perceived emotions. Many SER application systems often acquire and transmit speech data collected at the client-side to remot…

AttributeEmotion RecognitionFederated LearningInference Attack+1

An Attribute-Aligned Strategy for Learning Speech Representation

2021-06-05 · Yu-Lin Huang, Bo-Hao Su, Y. -W. Peter Hong, Chi-Chun Lee

Advancement in speech technology has brought convenience to our life. However, the concern is on the rise as speech signal contains multiple personal attributes, which would lead to either sensitive information leakage o…

AttributeEmotion RecognitionPrivacy PreservingSpeaker Verification+1

FastPFRec: A Fast Personalized Federated Recommendation with Secure Sharing

2026-03-18 · Zhenxing Yan, Jidong Yuan, Yongqi Sun, Haiyang Liu 외 arxiv

Graph neural network (GNN)-based federated recommendation systems effectively capture user-item relationships while preserving data privacy. However, existing methods often face slow convergence on graph data and privacy…

Recommendation SystemsGraph Neural Network

Privacy-Preserving Load Forecasting via Personalized Model Obfuscation

2023-11-21 · Shourya Bose, Yu Zhang, Kibaek Kim

The widespread adoption of smart meters provides access to detailed and localized load consumption data, suitable for training building-level load forecasting models. To mitigate privacy concerns stemming from model-indu…

Federated LearningLoad ForecastingmodelPrivacy Preserving