我的隐私在哪里？探索智能扬声器的意外触发
Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers
摘要：
像亚马逊的Alexa，谷歌的Assistant或苹果的Siri这样的语音助手已经成为智能扬声器的主要（语音）界面，可以在数百万家庭中找到。出于隐私原因，这些扬声器在将音频流上传到云端进行进一步处理之前，会分析其环境中的每一个声音，以获得相应的唤醒词，如“Alexa”或“Hey Siri”。以前的工作报告了不准确的唤醒词检测，它可以使用类似的单词或听起来像“可卡因面条”而不是“OK Google”。在本文中，我们对这种意外触发进行了全面的分析，即，例如，本不应该触发语音助手的声音，但却触发了。更具体地说，我们自动化了寻找意外触发器的过程，并使用电视节目、新闻和其他类型的音频数据集等日常媒体，测量了来自8家不同制造商的11款智能扬声器的普遍性。为了系统地检测意外触发器，我们描述了一种方法来人工制作这样的触发器使用发音字典和加权，基于电话的Levenshtein距离。总的来说，我们已经发现了数百个意外触发器。此外，我们还探讨了潜在的性别和语言偏见，并分析了再现性。最后，我们讨论了意外触发所产生的隐私影响，并探讨了减少和限制其对用户隐私的影响的对策。为了促进对这些误导机器学习模型的声音的进一步研究，我们发布了一个包含1000多个经过验证的触发器的数据集作为研究工件。
英文摘要：
Voice assistants like Amazon's Alexa, Google's Assistant, or Apple's Siri, have become the primary (voice) interface in smart speakers that can be found in millions of households. For privacy reasons, these speakers analyze every sound in their environment for their respective wake word like ''Alexa'' or ''Hey Siri,'' before uploading the audio stream to the cloud for further processing. Previous work reported on the inaccurate wake word detection, which can be tricked using similar words or sounds like ''cocaine noodles'' instead of ''OK Google.'' In this paper, we perform a comprehensive analysis of such accidental triggers, i.,e., sounds that should not have triggered the voice assistant, but did. More specifically, we automate the process of finding accidental triggers and measure their prevalence across 11 smart speakers from 8 different manufacturers using everyday media such as TV shows, news, and other kinds of audio datasets. To systematically detect accidental triggers, we describe a method to artificially craft such triggers using a pronouncing dictionary and a weighted, phone-based Levenshtein distance. In total, we have found hundreds of accidental triggers. Moreover, we explore potential gender and language biases and analyze the reproducibility. Finally, we discuss the resulting privacy implications of accidental triggers and explore countermeasures to reduce and limit their impact on users' privacy. To foster additional research on these sounds that mislead machine learning models, we publish a dataset of more than 1000 verified triggers as a research artifact.
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。
