Power information network security policy learning device and method based on attack and defence

A network security and policy learning technology, applied in the field of power information system security, can solve problems such as inapplicability of security policies, aggravating the complexity of problems, and dynamic changes.

Active Publication Date: 2018-08-07
JIANGSU ELECTRIC POWER CO
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although the methods of many researchers can be pre-designed and programmed for possible behaviors, as network security tasks become more and more complex, and the environment in the network is unknown, uncertain, and will change dynamically, thus

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Power information network security policy learning device and method based on attack and defence
  • Power information network security policy learning device and method based on attack and defence
  • Power information network security policy learning device and method based on attack and defence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0142] Below in conjunction with principle of the present invention, accompanying drawing and embodiment the present invention is further described

[0143] see figure 1 As shown, a power information network security policy learning device based on reinforcement learning agent attack and defense confrontation, including equipment network, several attack agents and several defense agents,

[0144] The device network is formed by connecting several device nodes 101-119 and lines according to the topology.

[0145] Several attacking agents attack the above-mentioned device network at the same time, and several defensive agents defend the above-mentioned several attacking agents at the same time. The above-mentioned several device nodes include general device nodes 101-109, 111-119 with relatively small losses after being invaded, and nodes with relatively large losses after being invaded. Important device node 110, the goal of the attacking agent is to invade an important device...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a power information network security policy learning device and method based on attack and defense. The device comprises a device network, attackers and defenders. A pluralityof attackers attack the device network at the same time. A plurality of defenders carry out defence at the same time. In an attack and defence process, the defenders improve defence capabilities for certain type of attacks through increase of defence values and improve detection capabilities for the certain type of attacks through increase of detection values. As the defence values are increased,the attackers invade device nodes harder and harder through utilization of a specific type, and the convenience for the other computer device nodes to employ the service of the computer device nodes is also reduced. Through increase of the detection values, the possibility that the device nodes detect the attacks successfully is also improved, and consumed computing resources are also increased. The total defence value and detection value of the whole network are smaller than or equal to preset values. Through simulation of the attack and defence, the optimum security policy is obtained with the minimum defence and detection cost.

Description

technical field [0001] The invention relates to the security field of electric power information systems, in particular to a device and method for learning security strategies of electric power information networks based on attack-defense confrontation. Background technique [0002] The power system is an important basis for production and life in modern society. Effective power equipment management is the guarantee of power supply, and a large number of power information systems have emerged. In recent years, with the construction of electric power information system, the scale of related information network has been increasing, and the network has become more and more complex. How to learn and formulate information network security policies to effectively protect the network and provide security for members in the network is a complex task. In fact, there is a balance between computer security, convenience of use, and computing resources consumed: improving the security ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): H04L29/06
CPCH04L63/1408H04L63/20
Inventor 景栋盛杨钰薛劲松王芳朱斐
Owner JIANGSU ELECTRIC POWER CO
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products