Characterizing The Adversarial Vulnerability Of Speech Self-supervised Learning
2021 · Haibin Wu, Bo Zheng, Xu Li, et al.
Abstract
A leaderboard named Speech processing Universal PERformance Benchmark (SUPERB), which aims at benchmarking the performance of a shared self-supervised learning (SSL) speech model across various downstream speech tasks with minimal modification of architectures and small amount of data, has fueled the research for speech representation learning. The SUPERB demonstrates speech SSL upstream models improve the performance of various downstream tasks through just minimal adaptation. As the paradigm of the self-supervised learning upstream model followed by downstream tasks arouses more attention in the speech community, characterizing the adversarial robustness of such paradigm is of high priority. In this paper, we make the first attempt to investigate the adversarial vulnerability of such paradigm under the attacks from both zero-knowledge adversaries and limited-knowledge adversaries. The experimental results illustrate that the paradigm proposed by SUPERB is seriously vulnerable to limi
Authors
(none)
Tags
Stats
Related papers
- SUPERB @ SLT 2022: Challenge On Generalization And Efficiency Of Self-supervised Speech Representation Learning (2022)9.23
- ML-SUPERB: Multilingual Speech Universal Performance Benchmark (2023)12.47
- Unispeech-sat: Universal Speech Representation Learning With Speaker Aware Pre-training (2021)0.00
- Investigating Self-supervised Learning For Speech Enhancement And Separation (2022)13.44
- ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, And Datasets (2024)4.52
- Lebenchmark: A Reproducible Framework For Assessing Self-supervised Representation Learning From Speech (2021)11.39
- Analyzing The Factors Affecting Usefulness Of Self-supervised Pre-trained Representations For Speech Recognition (2022)0.00
- Pushing The Limits Of Unsupervised Unit Discovery For SSL Speech Representation (2023)6.34