On optimization of ad-blocking lists for mobile devices

Online advertisements and third-party web tracking has gained much attention in recent years. Advertisers gather as much data and information about the users to provide targeted advertisement. Though this leads to a better user experience, it comes at the cost of privacy intrusive tracking. To this end, ad-blocking lists (or filter-lists, blacklists) have been introduced which prevent third-party tracking. Ad-blocking lists operate in a crowd-sourced manner, where new tracking domains (or rules) are continuously added by privacy activists and the redundant domains are discarded from the filter-list. Over time, the number of rules added outgrow the number of rules omitted, making it hard to manage the filter-lists. We empirically observe that the filter-lists mostly detect different ad and tracking domains. The filter-lists also use less than 1% of their rules on Alexa top 5,000 websites. This suggests the need to curate optimized filter-lists that provide high coverage and require less time to scan for a given domain on mobile devices. We develop an aggregated and filtered blacklist that is more than 150 times less bulky, and provides the same coverage as the union of the blacklists on Alexa top 5,000 websites. We also develop an update mechanism to incorporate new ad and tracking domains in the aggregated and filtered blacklist in a resource efficient manner.