In the contemporary food sector, additives are crucial for enhancing the taste and safety of food products. Their correct application is vital for boosting food quality and security. Nonetheless, the misuse of these additives can endanger the well-being of consumers. Consequently, the creation of a reliable and precise detection system for food additives is paramount for safeguarding the safety of food items. This study presents a detection model for food additives that utilizes support vector machines (SVM), employing machine learning to process the spectral data of food samples for swift and precise identification. The findings indicate that the SVM model equipped with an RBF kernel excels in detecting food additives, demonstrating superior accuracy, sensitivity, specificity, and F1 score. This paper introduces an innovative approach to detecting food additives and offers significant insights for food safety research.