A Speech Adversarial Sample Detection Method Based on Manifold Learning
-
Published:2024-04-19
Issue:8
Volume:12
Page:1226
-
ISSN:2227-7390
-
Container-title:Mathematics
-
language:en
-
Short-container-title:Mathematics
Author:
Ma Xiao1, Xu Dongliang1, Yang Chenglin1ORCID, Li Panpan2, Li Dong1
Affiliation:
1. School of Computer Science and Technology, Shandong University, Weihai 264209, China 2. College of Information Science and Engineering, Jiaxing University, Jiaxing 314041, China
Abstract
Deep learning-based models have achieved impressive results across various practical fields. However, these models are susceptible to attacks. Recent research has demonstrated that adversarial samples can significantly decrease the accuracy of deep learning models. This susceptibility poses considerable challenges for their use in security applications. Various methods have been developed to enhance model robustness by training with more effective and generalized adversarial examples. However, these approaches tend to compromise model accuracy. Currently proposed detection methods mainly focus on speech adversarial samples generated by specified white-box attack models. In this study, leveraging manifold learning technology, a method is proposed to detect whether a speech input is an adversarial sample before feeding it into the recognition model. The method is designed to detect speech adversarial samples generated by black-box attack models and achieves a detection success rate of 84.73%. It identifies the low-dimensional manifold of training samples and measures the distance of a sample under investigation to this manifold to determine its adversarial nature. This technique enables the preprocessing detection of adversarial audio samples before their introduction into the deep learning model, thereby preventing adversarial attacks without affecting model robustness.
Funder
Shandong Provincial Natural Science Foundation basic scientific research operating expenses of Shandong University National Natural Science Foundation of China Young Scholars Program of Shandong University, Weihai Science and Technology Development Plan of Weihai City
Reference34 articles.
1. Can AI artifacts influence human cognition? The effects of artificial autonomy in intelligent personal assistants;Hu;Int. J. Inf. Manag.,2021 2. Wang, D., Wang, X., and Lv, S. (2019). An Overview of End-to-End Automatic Speech Recognition. Symmetry, 11. 3. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv. 4. Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Berkay Celik, Z., and Swami, A. (2015). The Limitations of Deep Learning in Adversarial Settings. arXiv. 5. Pedraza, A., Deniz, O., and Bueno, G. (2021). On the Relationship between Generalization and Robustness to Adversarial Examples. Symmetry, 13.
|
|