Chaotic Random Knowledge Recognition Model for Secure Data Encryption in Network Communication

Abstract

To tackle privacy concerns in network communication security information, several experts recommend raising noise before data publication to safeguard user anonymity. However, this strategy may reduce experiment accuracy, making it inappropriate for circumstances that need exact data collecting and processing. Other ways, such as using chaotic algorithms and the GMW compiler to generate a chaotic random knowledge recognition model, have been suggested, however, they are hampered by their complexity and lack of logic and computational resilience. This paper presents a chaotic random knowledge recognition model to address these constraints by combining a log system that records the whole system in real-time and a configuration center that allows for smooth interaction among users. A set of computer tests were conducted to assess the model's usefulness, comparing it against classic DBSCAN and k-means clustering techniques. The results show that the proposed approach has clustering accuracy equivalent to conventional DBSCAN while greatly increasing operational efficiency. Furthermore, the model's encryption time was compared to existing cryptographic algorithms such as RSA-3DES, RSA-AES, and Hybrid Logistic Map-based Cryptography. The suggested model outperformed conventional approaches in terms of encryption speed over a range of packet sizes, demonstrating its promise for secure and effective data encryption in network communications. These results indicate that the chaotic random knowledge recognition model is a potential solution for safe data processing in contexts that need both accuracy and speed