EmoAttack：利用情感语音转换对深度语音分类模型实施语音后门攻击
EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models
AI总结：
本文提出 EmoAttack，将情感语音转换作为后门触发器攻击关键词检出与说话人验证模型，实验证明其攻击成功率高且强烈情感更适合作目标。
摘要：
深度语音分类任务主要包括关键词检出和说话人验证，在基于语音的人机交互中发挥着关键作用。近来，这些技术的安全性已被证明容易受到后门攻击。具体而言，在现有触发器中，语音样本会受到噪声干扰和组件修改的攻击。我们认为，语音后门攻击可以从策略上聚焦于情感这一语音固有的更高级主观感知属性。此外，我们提出情感语音转换技术可以作为语音后门攻击触发器，并将该方法称为 EmoAttack。基于此，我们在两项语音分类任务上开展了攻击实验，结果表明 EmoAttack 方法具有有效的触发器作用，以及显著的攻击成功率和准确率变化。此外，消融实验发现，带有强烈情感的语音更适合作为攻击目标。
英文摘要：
Deep speech classification tasks, mainly including keyword spotting and speaker verification, play a crucial role in speech-based human-computer interaction. Recently, the security of these technologies has been demonstrated to be vulnerable to backdoor attacks. Specifically speaking, speech samples are attacked by noisy disruption and component modification in present triggers. We suggest that speech backdoor attacks can strategically focus on emotion, a higher-level subjective perceptual attribute inherent in speech. Furthermore, we proposed that emotional voice conversion technology can serve as the speech backdoor attack trigger, and the method is called EmoAttack. Based on this, we conducted attack experiments on two speech classification tasks, showcasing that EmoAttack method owns impactful trigger effectiveness and its remarkable attack success rate and accuracy variance. Additionally, the ablation experiments found that speech with intensive emotion is more suitable to be targeted for attacks.
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。
