With the development of artificial intelligence, people begin to pay attention to the protection of sensitive information and data. Therefore, a homomorphic encryption framework based on effective integer vector is proposed and applied to deep learning to protect the privacy of users in binary convolutional neural network model. The conclusion shows that the model can achieve high accuracy. The training is 93.75% in MNIST dataset and 89.24% in original dataset. Because of the confidentiality of data, the training accuracy of the training set is only 86.77%. After increasing the training period, the accuracy began to converge to about 300 cycles, and finally reached about 86.39%. In addition, after taking the absolute value of the elements in the encryption matrix, the training accuracy of the model is 88.79%, and the test accuracy is 85.12%. The improved model is also compared with the traditional model. This model can reduce the storage consumption in the model calculation process, effectively improve the calculation speed, and have little impact on the accuracy. Specifically, the speed of the improved model is 58 times that of the traditional CNN model, and the storage consumption is 1/32 of that of the traditional CNN model. Therefore, homomorphic encryption can be applied to information encryption under the background of big data, and the privacy of the neural network can be realized.
With the widespread use of embedded systems, chaos is a nonlinear system with certainty and complexity. It is an important topic in the field of information security at present, and it is an effective way to apply to embedded systems. It has great practical value in theory and in practice. This research mainly focuses on the encryption technology of SQLite embedded database and proposes an improved sparrow algorithm (Logistic Chaos Sparrow Search Algorithm, LCSSA) based on Logistic Chaos Map. It shows that the security level of SQLite in web development is higher than that of conventional Access. The population is initialized by the logistic chaotic mapping method, which improves the quality of the initial solution, increases the diversity of the population, and reduces the risk of premature maturity of the algorithm. The initial value y 0 determines the encryption method of the nonlinear function. Taking the integer variable (int) as an example, the value range is -231~231. It can be seen that the key space is sufficient to prevent various conventional attacks. When the key is the wrong key, decryption will not yield any data. It can be found that encryption and decryption are very sensitive to the key, which is also determined by the sensitivity of chaotic encryption system to the initial value. The benchmark function compares the performance of the improved algorithm with the algorithm before the improvement and compares it with the SSA. The LCSSA has better convergence performance, higher accuracy, and better stability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.