Recent years have witnessed a sharp increase of malicious apps that steal users' personal information. To address users' concerns about privacy risks and to comply with data protection laws, more and more apps are supplied with privacy policies written in natural language to help users to understand an app's privacy practices. However, little is known whether these privacy policies are trustworthy or not. Questionable privacy policies may be prepared by careless app developers or someone with malicious intention. In this paper, we carry out a systematic study on privacy policy by proposing a novel approach to automatically identify five kinds of problems in privacy policy. After tackling several challenging issues, we implement the approach in a system, named PPChecker, and evaluate it with real apps and their privacy policies. The experimental results show that PPChecker can effectively identify questionable privacy policies with high precision. Applying PPChecker to 2,044 popular apps, we find that 1,429 apps (i.e., 69.9\%) have at least one kind of problems. This study sheds light on the research of improving and regulating apps' privacy policies.

中文翻译：

---

PPChecker：获取 Android 应用隐私政策的可信度

近年来，窃取用户个人信息的恶意应用程序急剧增加。为了解决用户对隐私风险的担忧并遵守数据保护法律，越来越多的应用程序提供了以自然语言编写的隐私政策，以帮助用户了解应用程序的隐私惯例。然而，这些隐私政策是否值得信赖却鲜为人知。有问题的隐私政策可能由粗心的应用程序开发人员或怀有恶意的人准备。在本文中，我们通过提出一种自动识别隐私政策中的五种问题的新方法，对隐私政策进行了系统研究。在解决了几个具有挑战性的问题后，我们在名为 PPChecker 的系统中实施了该方法，并使用真实的应用程序及其隐私政策对其进行了评估。实验结果表明，PPChecker 可以有效、高精度地识别有问题的隐私策略。将 PPChecker 应用于 2,044 个流行应用程序，我们发现 1,429 个应用程序（即 69.9\%）至少存在一种问题。这项研究阐明了改进和规范应用程序隐私政策的研究。