Wednesday, May 30, 2018

"Brave’s Chief Scientist, Dr. Ben Livshits, worked with Peter Snyder, a privacy researcher at Brave, and researchers from the University of Iowa (Umar Iqbal* and Zubair Shafiq) and the University of California Riverside (Shitong Zhu and Zhiyun Qian) on this project. The full paper can be downloaded from ArXiV.org here. The team is looking at deploying these techniques within Brave over time.

The team explained that filter lists are widely deployed by ad blockers to block ads in web browsers; however, these filter lists are manually curated based on informal crowdsourced feedback, which brings a number of maintenance challenges. AdGraph addresses these challenges with an approach that relies on information obtained from multiple layers of the web stack (HTML, HTTP, and JavaScript) to train a machine learning classifier to block both ads and trackers." ( | May 25, 2018)

More on this at c|net: "Brave's AI blocks ads better than today's browser plug-ins, company says" (May 25, 2018), at Scientific American: "Where Will the Ad versus Ad Blocker Arms Race End?" (May 31, 2018), and on Prof. Shafiq' twitter feed.

 

Paper abstract:

Filter lists are widely deployed by adblockers to block ads and other forms of undesirable content in web browsers. However, these filter lists are manually curated based on informal crowdsourced feedback, which brings with it a significant number of maintenance challenges. To address these challenges, we propose a machine learning approach for automatic and effective adblocking called AdGraph. Our approach relies on information obtained from multiple layers of the web stack (HTML, HTTP, and JavaScript) to train a machine learning classifier to block ads and trackers. Our evaluation on Alexa top-10K websites shows that AdGraph automatically and effectively blocks ads and trackers with 97.7% accuracy. Our manual analysis shows that AdGraph has better recall than filter lists, it blocks 16% more ads and trackers with 65% accuracy. We also show that AdGraph is fairly robust against adversarial obfuscation by publishers and advertisers that bypass filter lists.

 

* Iqbal lead the research