Research on Network Security Spatial Data Asset Deduplication Technology Based on Neural Networks

• Published in: 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI) pp. 469 - 474
• Main Authors: Meng, Chunzhi, Zeng, Mingfei, Meng, Liang, Pan, Junbing
• Format: Conference Proceeding
• Language: English
• Published: IEEE 31.05.2024
• Subjects: Accuracy; data assets; Data security; deduplication technology; Deep learning; Feature extraction; Network security; Neural networks; Resists; Spatial databases
• DOI: 10.1109/ICECAI62591.2024.10675112

With the rapid development of network technology, network security issues have become increasingly prominent, especially the serious threat posed by data leaks and network attacks to data security. In order to enhance network security and improve the utilization of data assets, this study proposes a network security spatial data asset deduplication technique that integrates Convolutional Neural Networks (CNN) and Long Short Term Memory Networks (LSTM). This technology significantly improves the accuracy and precision of deduplication through efficient feature extraction and matching comparison using deep learning algorithms. CNN is used to capture local patterns and structural features of data, while LSTM is used to model temporal dependencies of sequential data. The combination of the two significantly improves the efficiency and security of deduplication techniques. Compared with traditional deduplication techniques, this technology not only improves deduplication efficiency, but also enhances the processing ability for complex data types and can resist malicious attacks to a certain extent. The experimental results show that the proposed technology is superior to traditional methods in accuracy and recall, and has practical application value, providing a new direction for future technological development.