加密数据的检测方法及装置、非易失性存储介质
By extracting the dynamic, angular, and scale features of encrypted data streams and using anomaly detection models to analyze power grid communication data, the problem of existing technologies being unable to detect attack information in encrypted data streams without decryption is solved, thus improving the accuracy and efficiency of power grid network security detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- STATE GRID BEIJING ELECTRIC POWER CO
- Filing Date
- 2025-02-12
- Publication Date
- 2026-07-17
AI Technical Summary
The lack of existing technologies allows for the analysis of encrypted data streams without decryption to determine the presence of malicious information, rendering cybersecurity tools ineffective in detecting malicious traffic within encrypted data streams.
By acquiring the dynamic, angular, and scale features of the encrypted data stream, these features are processed and analyzed using an anomaly detection model. Features are extracted using Gram Angular Field Difference Map (GADF), Gram Angular Field Sum Map (GASF), and Markov Transformation Matrix (MTF) techniques, and anomaly detection is performed in conjunction with a convolutional neural network.
It enables the analysis of encrypted data streams without decryption, improving the accuracy and efficiency of detecting attack information in encrypted data streams and enhancing network security detection capabilities.
Smart Images
Figure CN120105450B_ABST