Did you hear that? Adversarial Examples Against Automatic Speech Recognition
arXiv:1801.00554
Abstract
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.
Published in NIPS 2017 Machine Deception workshop
References in corpus (3)
Cited by in corpus (48)
- Robust Audio Adversarial Example for a Physical Attack
- Characterizing Audio Adversarial Examples Using Temporal Dependency
- Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
- Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement
- Adversarial Examples in Modern Machine Learning: A Review
- Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition
- Weighted-Sampling Audio Adversarial Example Attack
- Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness
- Universal Adversarial Audio Perturbations
- Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues
- L2-Nonexpansive Neural Networks
- An Overview of Vulnerabilities of Voice Controlled Systems
- GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
- Universal adversarial examples in speech command classification
- Semantics and explanation: why counterfactual explanations produce adversarial examples in deep neural networks
- Perceptual Based Adversarial Audio Attacks
- Adversarial attacks on Copyright Detection Systems
- Geometry-Inspired Top-k Adversarial Perturbations
- Identifying Audio Adversarial Examples via Anomalous Pattern Detection
- Adversarial Learning of Deepfakes in Accounting
- WaveGuard: Understanding and Mitigating Audio Adversarial Examples
- Real-Time Adversarial Attacks
- Detecting Adversarial Attacks On Audiovisual Speech Recognition
- A Multiversion Programming Inspired Approach to Detecting Audio Adversarial Examples
- SEC4SR: A Security Analysis Platform for Speaker Recognition
- Defending Your Voice: Adversarial Attack on Voice Conversion
- Random Directional Attack for Fooling Deep Neural Networks
- A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization
- Grey-box Adversarial Attack And Defence For Sentiment Classification
- Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning
- Adversarial Example Detection by Classification for Deep Speech Recognition
- LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications
- Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent
- PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack
- Dompteur: Taming Audio Adversarial Examples
- DoPa: A Comprehensive CNN Detection Methodology against Physical Adversarial Attacks
- A Tandem Framework Balancing Privacy and Security for Voice User Interfaces
- Practical Attacks on Voice Spoofing Countermeasures
- A GAN-based Approach for Mitigating Inference Attacks in Smart Home Environment
- On the human evaluation of audio adversarial examples
- Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models
- Context-Aware Image Denoising with Auto-Threshold Canny Edge Detection to Suppress Adversarial Perturbation
- Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems
- Learning to fool the speaker recognition
- Self-Gradient Networks
- Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions
- Generating Watermarked Adversarial Texts
- Universal Physical Camouflage Attacks on Object Detectors