DescribeCtx: Context-Aware Description Synthesis for Sensitive Behaviors in Mobile Apps
DescribeCtx: Context-Aware Description Synthesis for Sensitive Behaviors in Mobile Apps
复制标题
DOI：
10.1145/3510003.3510058
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Shao Yang;Yuehan Wang;Y. Yao;Haoyu Wang;Yanfang Ye;Xusheng Xiao
中科院分区：
文献类型：
--
作者：
Shao Yang;Yuehan Wang;Y. Yao;Haoyu Wang;Yanfang Ye;Xusheng Xiao
虽然移动的应用（即，应用程序）变得能够处理来自用户的各种需求，他们对敏感数据的访问增加引起了隐私问题。为了向用户通知这种敏感行为，现有技术提出从应用描述中自动识别解释性语句;然而，许多敏感行为在对应的应用描述中没有解释。也存在将代码翻译成句子的通用技术。然而，这些技术缺乏解释敏感数据的使用的词汇表，并且没有考虑上下文（即，应用程序功能）的敏感行为。为了解决这些限制，我们提出了Describectx，这是一种上下文感知的描述合成方法，它使用大量流行的应用程序来训练神经机器翻译模型，并为敏感行为生成特定于应用程序的描述。具体地，Describectx将三个异构源编码为输入，即，由隐私策略提供的词汇表、由代码中的调用图提供的行为摘要以及由GUI文本提供的上下文信息。我们对1，262个Android应用程序的评估表明，与现有基线相比，Describectx产生了更准确的描述（BLEU中为24.96），并且在应用程序描述中手动识别的参考句子方面获得了更高的用户评分。
While mobile applications (i.e., apps) are becoming capable of handling various needs from users, their increasing access to sensitive data raises privacy concerns. To inform such sensitive behaviors to users, existing techniques propose to automatically identify explanatory sentences from app descriptions; however, many sensitive behaviors are not explained in the corresponding app descriptions. There also exist general techniques that translate code to sentences. However, these techniques lack the vocabulary to explain the uses of sensitive data and fail to consider the context (i.e., the app functionalities) of the sensitive behaviors. To address these limitations, we propose Describectx, a context-aware description synthesis approach that trains a neural machine translation model using a large set of popular apps, and generates app-specific descriptions for sensitive behaviors. Specifically, Describectx encodes three heterogeneous sources as input, i.e., vocabularies provided by privacy policies, behavior summary provided by the call graphs in code, and contextual information provided by GUI texts. Our evaluations on 1,262 Android apps show that, compared with existing baselines, Describectx produces more accurate descriptions (24.96 in BLEU) and achieves higher user ratings with respect to the reference sen-tences manually identified in the app descriptions.