Weighted-Sampling Audio Adversarial Example Attack.
Xiaolei Liu,Kun Wan,Yufei Ding,Xiaosong Zhang,Qingxin Zhu +4 more
- 03 Apr 2020
- Vol. 34, Iss: 04, pp 4908-4915
TL;DR: Weighted-sampling audio adversarial examples are proposed, focusing on the numbers and the weights of distortion to reinforce the attack, and a denoising method in the loss function is applied to make the adversarial attack more imperceptible.
read more
Abstract: Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent potential attacks. Despite many research on this, the efficiency and the robustness of existing works are not yet satisfactory. In this paper, we propose weighted-sampling audio adversarial examples, focusing on the numbers and the weights of distortion to reinforce the attack. Further, we apply a denoising method in the loss function to make the adversarial attack more imperceptible. Experiments show that our method is the first in the field to generate audio adversarial examples with low noise and high audio robustness at the minute time-consuming level 1.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Towards Query-Efficient Adversarial Attacks Against Automatic Speech Recognition Systems
TL;DR: This paper presents a novel and effective attack on ASR systems, named Selective Gradient Estimation Attack (SGEA), which only needs limited access to the output probabilities of neural networks, and achieves extremely high efficiency and success rates.
66
Adversarial Attacks and Defenses in Deep Learning: From a Perspective of Cybersecurity
TL;DR: This paper attempts to offer the first analysis framework for a systematic understanding of adversarial attacks, built from the perspective of cybersecurity so as to provide a lifecycle for adversarial attacked and defenses.
65
Adversarial Examples Attack and Countermeasure for Speech Recognition System: A Survey
Donghua Wang,Rangding Wang,Li Dong,Diqun Yan,Xueyuan Zhang,Yongkang Gong +5 more
- 30 Oct 2020
TL;DR: A systematic survey on the speech adversarial examples and several promising research directions on both making the attack constructing more realistic and the acoustic system more robust, respectively are given.
25
A low-query black-box adversarial attack based on transferability
TL;DR: Zhang et al. as discussed by the authors proposed a low-query black-box adversarial attack based on transferability by combining the optimization-based method and the transfer-based approach.
17
Spoofing Speaker Verification System by Adversarial Examples Leveraging the Generalized Speaker Difference
TL;DR: Wang et al. as discussed by the authors proposed an attack to spoof the speaker verification system based on generalized end-to-end (GE2E) loss function for misclassifying illegal users into the authentic user.
References
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
Nonlinear total variation based noise removal algorithms
TL;DR: In this article, a constrained optimization type of numerical algorithm for removing noise from images is presented, where the total variation of the image is minimized subject to constraints involving the statistics of the noise.
17.3K
•Proceedings Article
Intriguing properties of neural networks
Christian Szegedy,Wojciech Zaremba,Ilya Sutskever,Joan Bruna,Dumitru Erhan,Ian Goodfellow,Rob Fergus,Rob Fergus +7 more
- 01 Jan 2014
TL;DR: It is found that there is no distinction between individual highlevel units and random linear combinations of high level units, according to various methods of unit analysis, and it is suggested that it is the space, rather than the individual units, that contains of the semantic information in the high layers of neural networks.
13K
Towards Evaluating the Robustness of Neural Networks
Nicholas Carlini,David Wagner +1 more
- 22 May 2017
TL;DR: In this paper, the authors demonstrate that defensive distillation does not significantly increase the robustness of neural networks by introducing three new attack algorithms that are successful on both distilled and undistilled neural networks with 100% probability.
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
Alex Graves,Santiago Fernández,Faustino Gomez,Jürgen Schmidhuber +3 more
- 25 Jun 2006
TL;DR: This paper presents a novel method for training RNNs to label unsegmented sequences directly, thereby solving both problems of sequence learning and post-processing.
6.8K