ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio
Adversarial machine learning research has recently demonstrated the feasibility to confuse automatic speech recognition (ASR) models by introducing acoustically imperceptible perturbations to audio samples. To help researchers and practitioners gain better understanding of the impact of such attacks, and to provide them with tools to help them more easily evaluate and craft strong defenses for their models, we present ADAGIO, the first tool designed to allow interactive experimentation with adversarial attacks and defenses on an ASR model in real time, both visually and aurally. ADAGIO incorporates AMR and MP3 audio compression techniques as defenses, which users can interactively apply to attacked audio samples. We show that these techniques, which are based on psychoacoustic principles, effectively eliminate targeted attacks, reducing the attack success rate from 92.5% to 0%. We will demonstrate ADAGIO and invite the audience to try it on the Mozilla Common Voice dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAudio CompressionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Buffer Zone based Defense against Adversarial Examples in Image Classification
Recent defenses published at venues like NIPS, ICML, ICLR and CVPR are mainly focused on mitigating white-box attacks. These defenses do not properly consider adaptive adversaries. In this paper, we expand the scope of t…
Adversarial RobustnessClassificationGeneral Classificationimage-classification+1Attacking and Securing Community Detection: A Game-Theoretic Framework
It has been demonstrated that adversarial graphs, i.e., graphs with imperceptible perturbations, can cause deep graph models to fail on classification tasks. In this work, we extend the concept of adversarial graphs to t…
Community DetectionDefense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble
Although deep neural networks have achieved prominent performance on many NLP tasks, they are vulnerable to adversarial examples. We propose Dirichlet Neighborhood Ensemble (DNE), a randomized method for training a robus…
SentenceDefense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
Despite neural networks have achieved prominent performance on many natural language processing (NLP) tasks, they are vulnerable to adversarial examples. In this paper, we propose Dirichlet Neighborhood Ensemble (DNE), a…
SentenceBUZz: BUffer Zones for defending adversarial examples in image classification
We propose a novel defense against all existing gradient based adversarial attacks on deep neural networks for image classification problems. Our defense is based on a combination of deep neural networks and simple image…
ClassificationGeneral Classificationimage-classificationImage Classification