no code implementations • 14 Jul 2022 • Mohammad Esmaeilpour, Nourhene Chaalia, Patrick Cardinal
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.
no code implementations • 24 May 2022 • Mohammad Esmaeilpour, Nourhene Chaalia, Adel Abusitta, Francois-Xavier Devailly, Wissem Maazoun, Patrick Cardinal
We refer to this noble definition as compound conditional vector and employ it for training the generator network.
no code implementations • 14 Apr 2022 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
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.
no code implementations • 12 Nov 2021 • Mohammad Esmaeilpour, Nourhene Chaalia, Adel Abusitta, Francois-Xavier Devailly, Wissem Maazoun, Patrick Cardinal
This paper introduces a bi-discriminator GAN for synthesizing tabular datasets containing continuous, binary, and discrete columns.
no code implementations • 15 Mar 2021 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo.
no code implementations • 15 Mar 2021 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
This paper introduces a defense approach against end-to-end adversarial attacks developed for cutting-edge speech-to-text systems.
no code implementations • 22 Oct 2020 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
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.
no code implementations • 12 Oct 2020 • Mohammad Esmaeilpour, Raymel Alfonso Sallo, Olivier St-Georges, Patrick Cardinal, Alessandro Lameiras Koerich
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.
no code implementations • 26 Aug 2020 • Raymel Alfonso Sallo, Mohammad Esmaeilpour, Patrick Cardinal
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.
no code implementations • 12 Aug 2020 • Mohammad Esmaeilpour, Raymel Alfonso Sallo, Olivier St-Georges, Patrick Cardinal, Alessandro Lameiras Koerich
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.
no code implementations • 27 Jul 2020 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
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.
no code implementations • 26 Oct 2019 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
Adversarial attacks have always been a serious threat for any data-driven model.
1 code implementation • 22 Oct 2019 • Karl Michel Koerich, Mohammad Esmaeilpour, Sajjad Abdoli, Alceu de Souza Britto Jr., Alessandro Lameiras Koerich
Furthermore, the audio waveforms reconstructed from the perturbed spectrograms are also able to fool a 1D CNN trained on the original audio.
no code implementations • 24 Apr 2019 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
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.
no code implementations • 8 Apr 2019 • Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich
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.