Search Results for author:
Found 15 papers, 1 papers with code
RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks
This paper introduces a new synthesis-based defense algorithm for counteracting with a varieties of adversarial attacks developed for challenging the performance of the cutting-edge speech-to-text transcription systems.
RCC-GAN: Regularized Compound Conditional GAN for Large-Scale Tabular Data Synthesis
We refer to this noble definition as compound conditional vector and employ it for training the generator network.
From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks
This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network, namely ResNet-18.
Bi-Discriminator Class-Conditional Tabular GAN
This paper introduces a bi-discriminator GAN for synthesizing tabular datasets containing continuous, binary, and discrete columns.
Towards Robust Speech-to-Text Adversarial Attack
This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo.
Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems
This paper introduces a defense approach against end-to-end adversarial attacks developed for cutting-edge speech-to-text systems.
Class-Conditional Defense GAN Against End-to-End Speech Attacks
In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo.
Conditioning Trick for Training Stable GANs
In this paper we propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training.
Adversarially Training for Audio Classifiers
In this paper, we investigate the potential effect of the adversarially training on the robustness of six advanced deep neural networks against a variety of targeted and non-targeted adversarial attacks.
Improving Stability of LS-GANs for Audio and Speech Signals
In this paper we address the instability issue of generative adversarial network (GAN) by proposing a new similarity metric in unitary space of Schur decomposition for 2D representations of audio and speech signals.
From Sound Representation to Model Robustness
In this paper, we investigate the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network.
Detection of Adversarial Attacks and Characterization of Adversarial Subspace
Adversarial attacks have always been a serious threat for any data-driven model.
Cross-Representation Transferability of Adversarial Attacks: From Spectrograms to Audio Waveforms
Furthermore, the audio waveforms reconstructed from the perturbed spectrograms are also able to fool a 1D CNN trained on the original audio.
A Robust Approach for Securing Audio Classification Against Adversarial Attacks
In this paper we first review some strong adversarial attacks that may affect both audio signals and their 2D representations and evaluate the resiliency of the most common machine learning model, namely deep learning models and support vector machines (SVM) trained on 2D audio representations such as short time Fourier transform (STFT), discrete wavelet transform (DWT) and cross recurrent plot (CRP) against several state-of-the-art adversarial attacks.
Unsupervised Feature Learning for Environmental Sound Classification Using Weighted Cycle-Consistent Generative Adversarial Network
In this paper we propose a novel environmental sound classification approach incorporating unsupervised feature learning from codebook via spherical $K$-Means++ algorithm and a new architecture for high-level data augmentation.
