In the face of evolving security challenges, the integration of Internet of Things (IoT) and Artificial Intelligence (AI) technologies has become essential for modern building security systems. This paper explores the design and implementation of an intelligent building security system utilizing the Arduino GIGA R1 Wi-Fi, OV7670 camera, and Giga Display Shield, enhanced by Convolutional Neural Networks (CNNs). The system is designed to detect and respond to security threats in real-time, offering a proactive approach to building security. Leveraging the processing power of the Arduino platform and the image recognition capabilities of CNNs, the proposed system distinguishes between authorized and unauthorized access with a demonstrated accuracy of 92%. The study also identifies challenges, including performance in low-light conditions and communication delays, which affect the system's efficiency. Future work will focus on overcoming these limitations and further enhancing the system's functionality. The results indicate that the proposed solution is a promising step toward more intelligent and responsive building security systems, providing a foundation for further innovation in the field.