Adversarial Audio Detection Method Based on Transformer

Abstract

Speech recognition technology has been applied to all aspects of our daily life, but it faces many security issues. One of the major threats is the adversarial audio examples, which may tamper the recognition results of the acoustic speech recognition system (ASR). In this paper, we propose an adversarial detection framework to detect adversarial audio examples. The method is based on the transformer self-attention mechanism. Spectrogram features are extracted from the audio and divided into patches. Position information are embedded and then fed into transformer encoder. Experimental results show that the method achieves good performance with the detection accuracy of above 96.5% under the white-box attacks and blackbox attacks, and noisy circumstances. Even when detecting adversarial examples generated by the unknown attacks, it also achieves satisfactory results.