Towards Real-Time Web Tracking Detection with T.EX - The Transparency Extension

摘要

Targeted advertising is an inherent part of the modern Web as we know it. For this purpose, personal data is collected at large scale to optimize and personalize displayed advertisements to increase the probability that we click them. Anonymity and privacy are also important aspects of the World Wide Web since its beginning. Activists and developers relentlessly release tools that promise to protect us from Web tracking. Besides extensive blacklists to block Web trackers, researchers used machine learning techniques in the past years to automatically detect Web trackers. However, for this purpose often artificial data is used, which lacks in quality. Due to its sensitivity and the manual effort to collect it, real user data is avoided. Therefore, we present T.EX - The Transparency Extension, which aims to record a browsing session in a secure and privacy-preserving manner. We define requirements and objectives, which are used for the design of the tool. An implementation is presented, which is evaluated for its performance. The evaluation shows that our implementation can be used for the collection of data to feed machine learning algorithms.