DOAJ Open Access 2024

Silent-Hidden-Voice Attack on Speech Recognition System

Hyun Kwon Dooseo Park Ohyun Jo

Abstrak

In this paper, we propose a method for creating a hidden voice that is perceived as silence by a human. The proposed method creates a silent hidden voice that is mistakenly classified as a target phrase by the target model; it does this by configuring the loss function so that the probability of classification into the target phrase by the target model is highest. In an experimental evaluation using the Mozilla Common Voice dataset as the test data source and TensorFlow as the machine learning library, the proposed method created a silent hidden voice that had a 100% attack success rate for a target phrase on a target model while minimizing the average distortion to 187.81.

Topik & Kata Kunci

Electrical engineering. Electronics. Nuclear engineering

Penulis (3)

Hyun Kwon

Dooseo Park

Ohyun Jo

Format Sitasi

APA MLA BibTeX

Kwon, H., Park, D., Jo, O. (2024). Silent-Hidden-Voice Attack on Speech Recognition System. https://doi.org/10.1109/ACCESS.2022.3181194

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1109/ACCESS.2022.3181194

Informasi Jurnal

Tahun Terbit: 2024
Sumber Database: DOAJ
DOI: 10.1109/ACCESS.2022.3181194
Akses: Open Access ✓