This chapter provides a foundational understanding of federated learning (FL). FL represents a significant advance in the field of machine learning. This chapter begins with a definition of FL and a comparison with traditional learning paradigms. A discussion of data privacy concerns, regulatory requirements, and the need for scalable data processing is presented, which illustrates the shift from centralized to decentralized learning. Subsequently, the chapter discusses FL’s core principles and definitions, providing a necessary understanding of its framework. A number of significant milestones and technological advancements contributing to FL’s present state, as well as its historical evolution, are discussed in this chapter. The purpose of this introduction is to provide the foundation for a deeper exploration of federated learning’s applications and its impact on cybersecurity practices in future chapters. In a nutshell, this chapter explores the origins and development of FL and the collaborative efforts that contributed to its advancement. A discussion of FL’s significance within the cybersecurity domain concludes the chapter.