A QKD network anomaly detection method and related equipment
By using heterogeneous ensemble models and ensemble adversarial training, the problems of insufficient feature interaction modeling and robustness in QKD networks are solved, achieving high-precision and high-reliability anomaly detection, which is suitable for the secure operation and maintenance of quantum communication systems.
CN122437666APending Publication Date: 2026-07-21STATE GRID ANHUI ELECTRIC POWER CO LTD ELECTRIC POWER SCI RES INST +4
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID ANHUI ELECTRIC POWER CO LTD ELECTRIC POWER SCI RES INST
- Filing Date
- 2026-01-28
- Publication Date
- 2026-07-21
Smart Images
Figure CN122437666A_ABST
Abstract
The application discloses a QKD network anomaly detection method and related equipment, and the method comprises the following steps: inputting a multi-modal data set into a trained heterogeneous integrated model for processing to obtain a discrete prediction category set of a QKD network; performing hard voting decision fusion processing on the discrete prediction category prediction set of the QKD network to obtain a final detection result of the QKD network; and the heterogeneous integrated model comprises a Tab Transformer model, an Attention-MLP model and a Standard MLP model. The application can realize deep fusion and accurate representation of heterogeneous features, and significantly improve detection accuracy.
Need to check novelty before this filing date? Find Prior Art