Black box adversarial sample attack method for electric energy quality signal neural network classification model
A neural network model and power quality technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve problems such as economic loss to the grid, difficulty for attackers to obtain model architecture and parameter information, data loss, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0054] Such as figure 1 As shown, the power quality signals collected in the power system are transmitted to the designated signal classification module through the communication network. The signal classification module realizes the correct classification of signals by the trained deep learning (neural network) model, and according to the predicted classification results (ie figure 1 The "prediction type" in ) provides corresponding control instructions for the power system control center to adjust the operating state of the power grid. The attacker can invade the communication network of the power system, intercept the power measurement signal of the system, and generate the corresponding countermeasure signal (the difference between the confrontation signal and the original measurement signal is very small, and the system operator cannot detect the change), so that the neural network model can be classified incorrectly. It causes the power system control center to make wro...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com