Edge computing, referred to as the distributed computation paradigm, is revolutionizing industries by enabling data processing at the source so latency is reduced, bandwidth is improved, and real-time decision-making is enabled. Nevertheless, as the trend of edge computing continues to grow, new challenges of security and privacy have emerged. Edge systems are distributed systems that depend on numerous edge devices and edge nodes, and their decentralized nature can expose them to significant vulnerabilities at the same time, they process sensitive and personal data. In this chapter, we focus on AI and its importance in solving critical security challenges. AI-enabled security mechanisms such as intrusion detection systems, malware detection, and anomaly detection enable proactive defense against cyber-attacks. Artificial intelligence facilitates near-real-time monitoring and automated countermeasures, increasing the resilience of edge systems to an attack and lowering the impact of a security breach. It provides a brief of possible approaches to privacy preservation techniques, like federated learning, differential privacy, and AI-optimized encryption that will ensure the sensitive data is protected and never made public, whether it is at the edge. These techniques enable data to be analyzed and shared without risking user privacy, which is especially important in regulated industries like healthcare and finance. The chapter also offers practical insights using case studies from the real world in smart cities, healthcare edge computing, and autonomous vehicles. In all these cases, AI technologies are key in ensuring secure data flows, enhancing the reliability of systems, and ensuring that privacy remains intact while operational efficiency is maintained. Moreover, we provide insights into the future of edge security, including the potential for AI and blockchain combination to enhance data integrity and edge AI to secure IoT devices. It closes with a broader perspective on the future and potential challenges and opportunities within the field, including scalability, privacy-preserving AI models, and the regulatory landscape surrounding edge computing. The expansion of edge computing, coupled with the amalgamation of emerging technologies, will place unique requirements on AI and edge systems to further ensure that these networks are secure, efficient, and compliant with data directives.