Junior Submission
In recent years, web tracking has evolved as a major privacy concern on the Internet. Browser Fingerprinting could be considered as the most severe type of web tracking which takes advantage of web browsers inner features to obtain a unique fingerprint of users. Various methodologies have been proposed in order to combat browser fingerprinting. Most of them were based on static code analysis and the use of predefined blacklists. However, trackers are still able to fingerprint users by changing their techniques. As a result, previous methodologies which technically are signature-based cannot efficiently respond to new techniques. In this paper, we are proposing a comprehensive approach based on static analysis and machine learning to confront Browser Fingerprinting. Our proposed approach not only is able to identify unknown fingerprinting techniques, it also has a lower false positive rate.