Detecting Audio Attacks on ASR Systems with Dropout Uncertainty
Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show that our defense is able to detect attacks created through optimized perturbations and frequency masking on a state-of-the-art end-to-end ASR system. Furthermore, the defense can be made robust against attacks that are immune to noise reduction. We test our defense on Mozilla's CommonVoice dataset, the UrbanSound dataset, and an excerpt of the LibriSpeech dataset, showing that it achieves high detection accuracy in a wide range of scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification
Machine learning systems and also, specifically, automatic speech recognition (ASR) systems are vulnerable against adversarial attacks, where an attacker maliciously changes the input. In the case of ASR systems, the mos…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)One-Class Classificationspeech-recognition+2Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System
There are increasing concerns about malicious attacks on autonomous vehicles. In particular, inaudible voice command attacks pose a significant threat as voice commands become available in autonomous driving systems. How…
Autonomous DrivingAutonomous VehiclesOpen-Ended Question AnsweringSensor FusionPrior Networks for Detection of Adversarial Attacks
Adversarial examples are considered a serious issue for safety critical applications of AI, such as finance, autonomous vehicle control and medicinal applications. Though significant work has resulted in increased robust…
Adversarial AttackAdversarial Attack DetectionUncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout
Detecting surface landmines and unexploded ordnances (UXOs) using deep learning has shown promise in humanitarian demining. However, deterministic neural networks can be vulnerable to noisy conditions and adversarial att…
Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method
With the rapidly growing number of security-sensitive systems that use voice as the primary input, it becomes increasingly important to address these systems' potential vulnerability to replay attacks. Previous efforts t…