NeTS: Small: Collaborative Research: Leveraging Personalized Internet Services to Combat Online Trolling

information trackers and aggregators associated with a variety of online services. This includes, but is not limited to, trackers associated with web site recommendations, ad networks, search engines, online social networks, mobile applications, etc. These trackers are what supported the monetization of the Internet from a small non-profit network into a gigantic infrastructure that creates revenues measured in billions of dollars. Users have often reacted negatively to tracking systems, expressing concern about their lack of privacy and control over their personal data. Nonetheless, despite a substantial effort both on research and policy sides to expose and control this prevalent behavior, the reality is that users keep accepting updated online privacy policies, which in turn grant the gathering of more and more user personal data. Indeed, the vast majority of users, while aware of the increasing erosion of their online privacy, continue to use these valuable, often necessary, online services. In this project, we ask if it is possible to utilize the ubiquitous online tracking of users – for the direct benefit of the users themselves, as well as for the benefit of numerous distributed systems that rely upon open membership. On one hand, users face a contradiction: despite the fact that almost every browser click made over the last decade has been monitored by numerous online trackers, we, the users, often have a hard time proving our identity and uniqueness while using the Internet. On the other hand, many systems that rely upon open membership are often targets of online trolling, i.e., scenarios in which various groups deploy tactics to influence public opinion on the Internet, by leaving biased, false, misleading, and inauthentic comments, and then artificially amplifying their ratings. Online trolling is widely utilized, e.g., by various governments attempting to bias the public opinion, by political parties in online campaigns, or by numerous sellers seeking to improve the appeal of their products. Organized trolling has become a serious problem in today’s Internet; some argue that it can have a profound impact on the society and in particular on the future of democracy. We propose to combat online trolling by designing a system that would take direct advantage of the work online trackers do to record and interpret users’ behavior. Our key idea is to use the readily available personalized content, generated by online trackers in real-time, as a means to verify an online user’s uniqueness in a seamless and privacy-preserving manner. We propose to utilize such tracker-generated personalized content, submitted directly by the user, to construct a multi-tracker user-vector representation and use it in various online verification scenarios. The key goal of this project is to design, implement, and evaluate a personalizationbased counter-trolling service, and make it publicly available. Intellectual Merit: The proposed research will address fundamental questions that are key to developing and deploying a personalization-based counter-trolling service. The main research objectives are to explore the fundamental properties of user-vector representations, i.e., their construction, uniqueness, persistency, resilience, utility in online verification, etc. The key research questions are: How to detect and classify online trolling in the first place? How to scalably and automatically utilize personalized online services to combat online trolling? How to utilize the properties of the underlying personalized s