Skip to yearly menu bar Skip to main content

Workshop: A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning

Audio Injection Adversarial Example Attack

Xiaolei Liu · Xingshu Chen · Mingyong Yin · Yulong Wang · Teng Hu · Kangyi Ding


We study the problem of audio adversarial example attacks with sparse perturbations. Compared with image adversarial example attacks, attacking audio is more challenging because the audio structure is more complex and the perturbation is difficult to conceal. To overcome this challenge, we propose an audio injection adversarial example attack, which provides a new sight light to increase the concealment of attack behavior. Experiments demonstrate that the proposed audio injection adversarial example attack can significantly reduce the perturbation proportion and achieve a better attack effect than traditional attack methods.

Chat is not available.