Federated Learning-Based Personalized Recommendation Systems: An Overview on Security and Privacy Challenges

The recent advancement in next-generation Consumer Electronics (CE) has created the problems of information overload and information loss. The significance of Personalized Recommendation Systems (PRS) to efficiently and effectively extract useful user information is seen as an ideal solution to provide users with personalized content and services and therefore is used in different application domains including healthcare, e-commerce, social media, etc. Security and privacy are the two major challenges of the existing PRS for next-gen CE data. Federated learning (FL) has the potential to elevate the aforementioned challenges by sharing local recommender parameters while keeping all the training data on the device and therefore is seen as a promising technique to enhance security and privacy in PRS for the next-gen CE data. In this survey, we have first discussed the enhancement of the existing CE technologies, a holistic review of security and privacy challenges in current PRS, and the advantage of FL-based PRS for next-gen CE. Finally, we list a few open issues and challenges that can guide researchers and practitioners to further drive research in this promising area.