PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. The AAE architecture allows us to obtain good synthetic speech leveraging upon a discriminative training of latent vectors. Such synthetic speech is used to build a privacy-preserving classifier when non-sensitive data is not sufficiently available in the public domain. This classifier follows the PATE scheme that uses an ensemble of noisy outputs to label the synthetic samples and guarantee $\varepsilon$-differential privacy (DP) on its derived classifiers. Our proposed framework thus consists of an AAE-based generator and a PATE-based classifier (PATE-AAE). Evaluated on the Google Speech Commands Dataset Version II, the proposed PATE-AAE improves the average classification accuracy by +$2.11\%$ and +$6.60\%$, respectively, when compared with alternative privacy-preserving solutions, namely PATE-GAN and DP-GAN, while maintaining a strong level of privacy target at $\varepsilon$=0.01 with a fixed $\delta$=10$^{-5}$.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkKeyword SpottingPrivacy PreservingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PATE-TripleGAN: Privacy-Preserving Image Synthesis with Gaussian Differential Privacy
Conditional Generative Adversarial Networks (CGANs) exhibit significant potential in supervised learning model training by virtue of their ability to generate realistic labeled images. However, numerous studies have indi…
Image GenerationPrivacy PreservingDecentralized Differentially Private Segmentation with PATE
When it comes to preserving privacy in medical machine learning, two important considerations are (1) keeping data local to the institution and (2) avoiding inference of sensitive information from the trained model. Thes…
Brain Tumor SegmentationFederated LearningSegmentationSemantic Segmentation+1G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators
Recent advances in machine learning have largely benefited from the massive accessible training data. However, large-scale data sharing has raised great privacy concerns. In this work, we propose a novel privacy-preservi…
BIG-bench Machine LearningPrivacy PreservingThe Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging
Synthetic data created by differentially private (DP) generative models is increasingly used in real-world settings. In this context, PATE-GAN has emerged as one of the most popular algorithms, combining Generative Adver…
BenchmarkingScalable Differentially Private Data Generation via Private Aggregation of Teacher Ensembles
We present a novel approach named G-PATE for training differentially private data generator. The generator can be used to produce synthetic datasets with strong privacy guarantee while preserving high data utility. Our a…