As the use of cryptographic algorithms continues to expand in securing digital communications, the ability to accurately identify and classify these algorithms becomes increasingly important, particularly for cybersecurity, digital forensics, and data integrity monitoring. This paper presents an automated system for recognizing cryptographic algorithms using machine learning techniques. The proposed approach leverages feature extraction from encrypted data to train models that can accurately differentiate between various encryption algorithms such as AES, RSA, DES, and others. By employing supervised learning algorithms, including support vector machines, decision trees, and deep learning techniques, our model is capable of identifying cryptographic algorithms with high accuracy. The system is trained on a dataset of encrypted outputs, where specific characteristics, such as key length, block size, and data patterns, are used as responses to the machine learning model. The results determine the efficiency of machine learning in automating the recognition process, achieving a high detection rate while maintaining scalability and speed. This research paves the way for real-time identification of cryptographic techniques, enabling enhanced threat detection, malware analysis, and forensic investigation. Furthermore, it opens the door to future work in expanding the system to handle more complex and evolving encryption schemes.