Neural Network Based Data Encryption: A Comparison Study among DES, AES, and HE Techniques

Abstract

With the improvement of technology and the continuous expansion and deepening of neural network technology, its application in computer network security plays an important role. However, the development of neural networks is accompanied by new threats and challenges. This paper proposes to encrypt the weight data using encryption algorithms and embed image encryption algorithms to improve protected data security further. The purpose is to address the feasibility and effectiveness of using modern encryption algorithms for data encryption in machine learning in response to data privacy breaches. The approach consists of training a neural network to simulate a model of machine learning and then encrypting it using Data Encryption Standard (DES), Advanced Encryption Standard (AES), and Homomorphic Encryption (HE) techniques, respectively. Its performance is evaluated based on the encryption/decryption accuracy and computational efficiency. The results indicate that combining DES with Blowfish offers moderate encryption and decryption speeds but is less secure than AES and HE. AES provides a practical solution, balancing security and performance, offering a relatively swift encryption and decryption process while maintaining high security. However, Fernet and HE present a viable alternative if data privacy is a top priority. Encryption and decryption times increase with file size and require sufficient computational resources. Future research should explore image encryption techniques to balance security and accurate image retrieval during decryption. Advanced privacy-preserving approaches, such as differential privacy and secure multi-party computation, may enhance security and confidentiality in digital encryption and decryption processes.