Detection of Adversarial Attacks and Characterization of Adversarial Subspace

Such 2D representations have lower dimensionality than audio waveforms and they easily fit advanced deep learning architectures mainly developed for computer visi on applications. Mel frequency cepstral coefficient (MFCC), short-time Fourier transformation (STFT), discrete wavel et transformation (DWT) are among the most pervasive 2D signal representations which essentially visualize frequ ency-magnitude distribution of a given reconstructed signal ove r time. Thus far, the best sound classification accuracy has been achieved for deep learning algorithms trained on 2D signal representations [1, 2]. However, it has been shown th at despite achieving high performance, the approaches based on 2D representations are very vulnerable against adversar ial attacks [3]. Unfortunately, this poses a strict security is sue because crafted adversarial examples not only mislead the target model toward a wrong label, but also, they are transfe r-able to other models including conventional algorithms suc h as support vector machines (SVM) [3].