arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.01906eess.AScs.CRcs.LGcs.SDstat.ML
收藏

具有丢失不确定性的ASR系统音频攻击检测

Detecting Audio Attacks on ASR Systems with Dropout Uncertainty

Mitsubishi Electric Research Laboratories (MERL)(三菱电机研究实验室);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Tejas Jayashankar, Jonathan Le Roux, Pierre Moulin

摘要:

最近开发了各种对抗性音频攻击来欺骗自动语音识别(ASR)系统。我们在这里提出了一个防御这种攻击的基础上引入的不确定性神经网络中的辍学。我们表明,我们的防御能够检测到通过最先进的端到端ASR系统上的优化扰动和频率掩蔽创建的攻击。此外,可以使防御对不受噪声降低影响的攻击是鲁棒的。我们在Mozilla的CommonVoice数据集,UrbanSound数据集和LibriSpeech数据集的摘录上测试了我们的防御,表明它在广泛的场景中实现了高检测精度。

英文摘要:

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show that our defense is able to detect attacks created through optimized perturbations and frequency masking on a state-of-the-art end-to-end ASR system. Furthermore, the defense can be made robust against attacks that are immune to noise reduction. We test our defense on Mozilla's CommonVoice dataset, the UrbanSound dataset, and an excerpt of the LibriSpeech dataset, showing that it achieves high detection accuracy in a wide range of scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑