Visible to the public Novel Defense Method against Audio Adversarial Example for Speech-to-Text Transcription Neural Networks

TitleNovel Defense Method against Audio Adversarial Example for Speech-to-Text Transcription Neural Networks
Publication TypeConference Paper
Year of Publication2019
AuthorsTamura, Keiichi, Omagari, Akitada, Hashida, Shuichi
Conference Name2019 IEEE 11th International Workshop on Computational Intelligence and Applications (IWCIA)
Date Publishednov
Keywordsadversarial example, audio adversarial example, Collaboration, composability, computer security, data representation, Deep Learning, Deep Speech, defense method, learning (artificial intelligence), neural nets, Neural networks, policy-based governance, pubcrawl, sandbox approach, Sandbox Method, Sandboxing, security of data, Speech recognition, speech synthesis, speech-to-text, speech-to-text transcription neural networks
AbstractWith the developments in deep learning, the security of neural networks against vulnerabilities has become one of the most urgent research topics in deep learning. There are many types of security countermeasures. Adversarial examples and their defense methods, in particular, have been well-studied in recent years. An adversarial example is designed to make neural networks misclassify or produce inaccurate output. Audio adversarial examples are a type of adversarial example where the main target of attack is a speech-to-text transcription neural network. In this study, we propose a new defense method against audio adversarial examples for the speech-to-text transcription neural networks. It is difficult to determine whether an input waveform data representing the sound of voice is an audio adversarial example. Therefore, the main framework of the proposed defense method is based on a sandbox approach. To evaluate the proposed defense method, we used actual audio adversarial examples that were created on Deep Speech, which is a speech-to-text transcription neural network. We confirmed that our defense method can identify audio adversarial examples to protect speech-to-text systems.
DOI10.1109/IWCIA47330.2019.8955062
Citation Keytamura_novel_2019