Cryptographic Algorithm Identification through Machine Learning for Enhanced Data Security

This paper discusses the significance of identifying encryption algorithms in today's digital era to ensure data security. The study uses machine learning (ML) techniques, including Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbors (KNN), to develop a classification model for distinguishing between encryption algorithms like Blowfish, AES, and 3DES. Results show distinct performances among the algorithms, with SVM achieving a robust 91 % accuracy rate, Random Forest excelling in precision with a 99 % accuracy rate, and KNN providing reasonable but comparatively lower accuracy at 34 %. The findings underscore the diverse capabilities of ML algorithms in encryption algorithm identification, offering valuable insights for enhancing data security practices and emphasizing the importance of selecting the most suitable ML approach based on specific security requirements.