Speech Privacy Leakage from Shared Gradients in Distributed Learning
Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks are vulnerable to privacy leakage attacks from shared gradients. Despite extensive efforts in the image domain, the exploration of speech privacy leakage from gradients is quite limited. In this paper, we explore methods for recovering private speech/speaker information from the shared gradients in distributed learning settings. We conduct experiments on a keyword spotting model with two different types of speech features to quantify the amount of leaked information by measuring the similarity between the original and recovered speech signals. We further demonstrate the feasibility of inferring various levels of side-channel information, including speech content and speaker identity, under the distributed learning framework without accessing the user's data.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningKeyword SpottingSimilar Papers 제목 키워드 기반
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previ…
Analyzing Inference Privacy Risks Through Gradients in Machine Learning
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper …
AttributeGraphDLG: Exploring Deep Leakage from Gradients in Federated Graph Learning
Federated graph learning (FGL) has recently emerged as a promising privacy-preserving paradigm that enables distributed graph learning across multiple data owners. A critical privacy concern in federated learning is whet…
Federated LearningGraph LearningAttribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings
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+1FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users
The federated learning (FL) technique was developed to mitigate data privacy issues in the traditional machine learning paradigm. While FL ensures that a user's data always remain with the user, the gradients are shared …
Data PoisoningFederated LearningPrivacy Preserving