Privacy-Aware Personalization for Mobile Advertising

Mobile advertising is an increasingly important driver in the Internet economy. We point out fundamental trade-offs between important variables in the mobile advertisement ecosystem. In order to increase relevance, ad campaigns tend to become more targeted and personalized by using context information extracted from user’s interactions and smartphone’s sensors. This raises privacy concerns that are hard to overcome due to the limited resources (energy and bandwidth) available on the phones. We point out that in the absence of a trusted third party, it is impossible to maximize these three variables—ad relevance, privacy, and efficiency—in a single system. This leads to the natural question: can we formalize a common framework for personalized ad delivery that can be instantiated to any desired trade-off point? We propose such a flexible ad-delivery framework where personalization is done jointly by the server and the phone. We show that the underlying optimization problem is NP-hard and present an efficient algorithm with a tight approximation guarantee. Since tuning personalization rules requires implicit user feedback, such as clicks, we ask how can we, in an efficient and privacy preserving way, gather statistics over a dynamic population of mobile users? This is needed for end-to-end privacy of an ad system. We propose the first differentially-private distributed protocol that works even in the presence of a dynamic and malicious set of users. We evaluate our methods with a large click log of location-aware searches in Microsoft Bing for mobile. Our experiments show that our framework can simultaneously achieve reasonable levels of privacy, efficiency, and ad relevance and can efficiently support a high churn rate of users during the gathering statistics that are required for personalization.