mlsanityData to 14 Oct 2026

Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition

arXiv 2202.08532 ↗First posted 17 Feb 2022eess.AS cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

In this work, we aim to enhance the system robustness of end-to-end automatic speech recognition (ASR) against adversarially-noisy speech examples. We focus on a rigorous and empirical "closed-model adversarial robustness" setting (e.g., on-device or cloud applications). The adversarial noise is only generated by closed-model optimization (e.g., evolutionary and zeroth-order estimation) without accessing gradient information of a targeted ASR model directly. We propose an advanced Bayesian neural network (BNN) based adversarial detector, which could model latent distributions against adaptive adversarial perturbation with divergence measurement. We further simulate deployment scenarios of RNN Transducer, Conformer, and wav2vec-2.0 based ASR systems with the proposed adversarial detection system. Leveraging the proposed BNN based detection system, we improve detection rate by +2.77 to +5.42% (relative +3.03 to +6.26%) and reduce the word error rate by 5.02 to 7.47% on LibriSpeech datasets compared to the current model enhancement methods against the adversarial speech examples.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 17 Feb 2022.

Builds on

30 of 38 references.

References · 30

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  6. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  7. 2019On Evaluating Adversarial Robustnesscited by 447
  8. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  9. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  10. 2013Optimal rates for zero-order convex optimization: the power of two function evaluationscited by 198
  11. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 182
  12. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
18 more
  1. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  2. 2018Universal Adversarial Trainingcited by 87
  3. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  4. 2018Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Networkcited by 69
  5. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 65
  6. 2018Bayesian Layers: A Module for Neural Network Uncertaintycited by 57
  7. 2018Robust Audio Adversarial Example for a Physical Attackcited by 44
  8. 2018Characterizing Audio Adversarial Examples Using Temporal Dependencycited by 36
  9. 2020Multi-task Language Modeling for Improving Speech Recognition of Rare Wordscited by 21
  10. 2021Adversarial Attacks and Defenses for Speech Recognition Systemscited by 20
  11. 2020Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancementcited by 18
  12. 2021Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learningcited by 16
  13. 2019Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"cited by 12
  14. 2018Training Augmentation with Adversarial Examples for Robust Speech Recognitioncited by 11
  15. 2021PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classificationcited by 10
  16. 2018Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Settingcited by 8
  17. 2019Encrypted Speech Recognition using Deep Polynomial Networkscited by 8
  18. 2021Adversarial Examples Detection with Bayesian Neural Networkcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1.

2 papers.

  1. 2022An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognitioncited by 1
  2. 2024Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognitioncited by 1