Paper Info
Title
Adversarial Audio Attacks that Evade Temporal Dependency
Abstract
As the real-world applications (image segmentation, speech recognition, machine translation, etc.) are increasingly adopting Deep Neural Networks (DNNs), DNN’s vulnerabilities in a malicious environment have become an increasingly important research topic in adversarial machine learning. Adversarial machine learning (AML) focuses on exploring vulnerabilities and defensive techniques for machine learning models. Recent work has shown that most adversarial audio generation methods fail to consider audios’ temporal dependency (TD) (i.e., adversarial audios exhibit weaker TD than benign audios). As a result, the adversarial audios are easily detectable by examining their TD. Therefore, one area of interest in the audio AML community is to develop a novel attack that evades a TD-based detection model. In this contribution, we revisit the LSTM model for audio transcription and propose a new audio attack algorithm that evades the TD-based detection by explicitly controlling the TD in generated adversarial audios. The experimental results show that the detectability of our adversarial audio is significantly reduced compared to the state-of-the-art audio attack algorithms. Furthermore, experiments also show that our adversarial audios remain nearly indistinguishable from benign audios with only negligible perturbation magnitude.
Year
DOI
Venue
2020
10.1109/SSCI47803.2020.9308597
2020 IEEE Symposium Series on Computational Intelligence (SSCI)
Keywords
DocType
ISBN
state-of-the-art audio attack algorithms,benign audios,adversarial audio attacks,evade temporal dependency,adversarial machine learning,machine learning models,adversarial audio generation methods,audio AML community,audio transcription,audio attack algorithm,generated adversarial audios
Conference
978-1-7281-2548-0
Citations 
PageRank 
References 
0
0.34
0
Authors
2
Name
Order
Citations
PageRank
Heng Liu115327.10
Gregory Ditzler221416.55