Did you hear that? Adversarial Examples Against Automatic Speech Recognition

2018-01-02 · Moustafa Alzantot, Bharathan Balaji, Mani Srivastava

Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction between humans and machines. Recently, researchers have demonstrated powerful attacks against machine learning models that can fool them to produceincorrect results. However, nearly all previous research in adversarial attacks has focused on image recognition and object detection models. In this short paper, we present a first of its kind demonstration of adversarial attacks against speech classification model. Our algorithm performs targeted attacks with 87% success by adding small background noise without having to know the underlying model parameter and architecture. Our attack only changes the least significant bits of a subset of audio clip samples, and the noise does not change 89% the human listener's perception of the audio clip as evaluated in our human study.

📄 PDF Abstract BibTeX arXiv:1801.00554

Code (1)

nesl/adversarial_audio 공식 구현 tf

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)object-detection Object Detection speech-recognition Speech Recognition

Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition

2020-12-21 · Shoma Ishida, Satoshi Ono

This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the…

Adversarial Attack Automatic Speech Recognition Automatic Speech Recognition (ASR)speech-recognition+1

Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition

2018-09-11 · ROCLINGIJCLCLP 2018 10 · Krishan Rajaratnam, Kunal Shah, Jugal Kalita

An adversarial attack is an exploitative process in which minute alterations are made to natural inputs, causing the inputs to be misclassified by neural models. In the field of speech recognition, this has become an iss…

Adversarial Attack Automatic Speech Recognition Automatic Speech Recognition (ASR)speech-recognition+1

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

2022-02-17 · Chao-Han Huck Yang, Zeeshan Ahmed, Yile Gu, Joseph Szurley 외

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 robustnes…

Adversarial Robustness Automatic Speech Recognition Automatic Speech Recognition (ASR)Model Optimization+2

Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition

2018-12-25 · Krishan Rajaratnam, Jugal Kalita

Neural models enjoy widespread use across a variety of tasks and have grown to become crucial components of many industrial systems. Despite their effectiveness and extensive popularity, they are not without their exploi…

Automatic Speech Recognition Automatic Speech Recognition (ASR)speech-recognition Speech Recognition

Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems

2019-08-05 · Lea Schönherr, Thorsten Eisenhofer, Steffen Zeiler, Thorsten Holz 외

Automatic speech recognition (ASR) systems can be fooled via targeted adversarial examples, which induce the ASR to produce arbitrary transcriptions in response to altered audio signals. However, state-of-the-art adversa…