PBSM:基于音调提升和声音掩蔽的针对关键词定位的后门攻击
PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound masking
摘要:
关键词定位(KWS)已广泛应用于各种语音控制场景中。KWS的训练通常基于深度神经网络,需要大量的数据。制造商通常使用第三方数据来训练KWS。然而,深度神经网络对制造商来说并不具有足够的可解释性,攻击者可以操纵第三方训练数据,在模型训练期间植入后门。有效的后门攻击可以迫使模型在某些条件下做出指定的判断,即,触发器本文设计了一种基于音调提升和声音掩蔽的KWS后门攻击方案PBSM。实验结果表明,PBSM是可行的,达到平均攻击成功率接近90%,在三个受害者模型中毒小于1%的训练数据。
英文摘要:
Keyword spotting (KWS) has been widely used in various speech control scenarios. The training of KWS is usually based on deep neural networks and requires a large amount of data. Manufacturers often use third-party data to train KWS. However, deep neural networks are not sufficiently interpretable to manufacturers, and attackers can manipulate third-party training data to plant backdoors during the model training. An effective backdoor attack can force the model to make specified judgments under certain conditions, i.e., triggers. In this paper, we design a backdoor attack scheme based on Pitch Boosting and Sound Masking for KWS, called PBSM. Experimental results demonstrated that PBSM is feasible to achieve an average attack success rate close to 90% in three victim models when poisoning less than 1% of the training data.
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。