دانلود کتاب حفظ حریم خصوصی در یادگیری ماشینی

Our search queries, browsing history, purchase transactions, the videos we watch, and movie preferences are a few types of information that are being collected and stored daily. This data collection happens within our mobile devices and computers, on the streets, and even in our own offices and homes. Advances in artificial intelligence (AI) in the big data era have increased the capability to capitalize on and benefit from the collection of private data. Such private data is being used for a variety of machine learning (ML) applications in different domains, such as marketing, insurance, financial services, mobility, social networks, and healthcare. For instance, more and more cloud-based data-driven ML applications are being developed by different service providers (who can be classified as the data users, such as Facebook, LinkedIn, and Google). Most of these applications leverage the vast amount of data collected from each individual (the data owner) to offer certain valuable services to the users. These services are often being used to gain some commercial or political advantage by facilitating various types of user recommendations, activity recognition, health monitoring, targeted advertising, and even predicting election results. However, on the flip side, the same set of data could be repurposed/reproduced differently to infer certain sensitive (private) information, which would jeopardize the privacy of individuals. Moreover, with the increased popularity of Machine Learning as a Service (MLaaS), where cloud-based machine learning and computing resources are bundled together to provide efficient analytical platforms (e.g., Microsoft Azure Machine Learning Studio, AWS Machine Learning, and Google Cloud Machine Learning Engine), it is necessary to take different measures to enforce privacy on those services before use with sensitive datasets. This book is for intermediate-level data science enthusiasts of machine learning (i.e., people who have some experience with ML) who would like to know the privacy-preserving techniques for ML and how to implement them in practice and productionize for their own scenarios and use cases.