paper-with-me

Papers

Characterizing the adversarial vulnerability of speech self-supervised learning

2021-11-08 · Haibin Wu, Bo Zheng, Xu Li, Xixin Wu, Hung-Yi Lee, Helen Meng

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 limited-knowledge adversaries, and the attacks generated by zero-knowledge adversaries are with transferability. The XAB test verifies the imperceptibility of crafted adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2111.04330

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessBenchmarkingRepresentation LearningSelf-Supervised LearningSpeech Representation Learning

Similar Papers 제목 키워드 기반

Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection

2022-10-03 · Xuanjun Chen, Haibin Wu, Helen Meng, Hung-Yi Lee 외

Audio-visual active speaker detection (AVASD) is well-developed, and now is an indispensable front-end for several multi-modal applications. However, to the best of our knowledge, the adversarial robustness of AVASD mode…

Active Speaker DetectionAdversarial RobustnessAudio-Visual Active Speaker Detection

Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

2020-03-31 · Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Xiaoli Ma 외

Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhan…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationSpeech Enhancement+2

Adversarial Black-Box Attacks on Automatic Speech Recognition Systems using Multi-Objective Evolutionary Optimization

2018-11-04 · Shreya Khare, Rahul Aralikatte, Senthil Mani

Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains. Both black-box and white-box approaches have been used to either r…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense

2024-09-13 · Jeremy Styborski, Mingzhi Lyu, Yi Huang, Adams Kong

Availability poisons exploit supervised learning (SL) algorithms by introducing class-related shortcut features in images such that models trained on poisoned data are useless for real-world datasets. Self-supervised lea…

Self-Supervised Learning

Benchmarking Gaslighting Attacks Against Speech Large Language Models

2025-09-24 · Jinyang Wu, Bin Zhu, Xiandong Zou, Qiquan Zhang 외 arxiv

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has st…