PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification

2 Apr 2021  ·  Chao-Han Huck Yang, Sabato Marco Siniscalchi, Chin-Hui Lee ·

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$^{-5}$.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


Ranked #3 on Keyword Spotting on Google Speech Commands (10-keyword Speech Commands dataset metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Keyword Spotting Google Speech Commands PATE-AAE (Differentially-Private) 10-keyword Speech Commands dataset 92.37 # 3

Methods