Keynote Talk - Federated Learning: The Hype, State-of-the-Art and Open Challenges

The popularity of machine learning models has dramatically increased in a large variety of applications that affect people's daily lifes, including product recommendations, healthcare predictions and critical applications. This wide availability has at the same time raised questions about the trustworthiness, security, and privacy implications of using these systems. While novel technologies and methodologies have been emerging to protect the privacy and security of AI Systems, there are still open challenges that need to be addressed by the research community. Over the past years, my research has focused on the creation of defenses to protect the machine learning pipeline and the design of privacy-aware methodologies to enable the training of accurate machine learning models without transmitting the data to a central place. In this talk, I will focus on data privacy covering a game-changing paradigm known as federated learning [4], which to some extend addresses privacy concerns and regulations that prevent the free transmission and sharing of information. Federated learning is a technology that enables multiple participants owning private data to collaboratively train a single machine learning model while maintaining their training data locally. This is in sharp contrast to traditional machine learning where all data needs to be in a central place. Some argue that federated learning is a privacy-by-design technology given that it does not require data to be transmitted to a central place. However, there are still privacy risks that are relevant in some scenarios. Novel inference attacks that take advantage of the federated learning process have been demonstrated in the literature, resulting in a variety of defenses that aim to reduce these risks. I will present some of these attacks and several cryptographical and differential privacy techniques to deter them, including [5,7,8]. The plethora of defenses is particularly interesting given their diverse threat models and the divergent set of privacy requirements they address. In this talk I will demystify them. I will also explain some challenges related to manipulation attacks [6,9] and machine learning fairness [1] in the context of federated learning. Finally, I will touch upon transparency issues and how to enable accountability for regulated industries [2,3] and vertical federated learning [7]. This talk will go through the security and privacy challenges and solutions in federated learning systems.