论文标题
PBSM：基于俯仰和声音掩盖的关键字发现关键字发现的后门攻击
PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound masking
论文作者
论文摘要
关键字点（KWS）已被广泛用于各种语音控制场景。 KWS的培训通常基于深层神经网络，需要大量数据。制造商经常使用第三方数据来培训KWS。但是，深层神经网络对制造商不足以解释，攻击者可以操纵第三方训练数据，以在模型培训期间种植后门。有效的后门攻击可以迫使模型在某些条件下（即触发器）做出指定的判断。在本文中，我们根据KWS的俯仰增强和声音掩盖设计了一个后门攻击方案，称为PBSM。实验结果表明，在中毒少于训练数据的1％时，在三个受害者模型中，PBSM是可行的，可以在三个受害者模型中获得接近90％的平均攻击成功率。
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.
