Artificial Intelligence-Based Intelligent Scheduling Method and System for Penetration Testing

By constructing an initial task-dependent directed acyclic graph and a defense situation awareness model, and dynamically adjusting the penetration testing task topology, the problems of blocking and low efficiency in existing penetration testing under dynamic defense environments are solved, achieving adaptive scheduling and efficient penetration testing.

CN121664572BActive Publication Date: 2026-05-26BEIJING ZHONGKE ZHUOXIN SOFTWARE EVALUATION TECH CENT
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING ZHONGKE ZHUOXIN SOFTWARE EVALUATION TECH CENT
Filing Date
2026-02-09
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing penetration testing techniques struggle to adjust attack topology and pace in real time when facing dynamic defense mechanisms, leading to test tasks being easily blocked, low efficiency, and invalid packet sending. They also fail to balance the risks of vulnerability discovery and defense triggering in complex network environments.

Method used

An AI-based intelligent scheduling method for penetration testing is adopted. This method constructs an initial task dependency directed acyclic graph, captures the target system's response status in real time, builds a defense situation awareness model, dynamically adjusts the task execution graph, introduces a multi-target resource allocation strategy, and generates an adaptive scheduling instruction set to achieve adaptive scheduling for penetration testing.

Benefits of technology

It enables efficient execution of penetration tests in complex network environments, avoiding blocking and invalid packet sending due to defense mechanisms, thus improving penetration efficiency and security. It also achieves adaptive scheduling under different network bandwidths and defense strengths, ensuring the integrity and accuracy of test tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121664572B_ABST
    Figure CN121664572B_ABST
Patent Text Reader

Abstract

This invention relates to the field of network information security and automated penetration testing technology, specifically to an intelligent scheduling method and system for penetration testing based on artificial intelligence. The method includes: S1, collecting asset fingerprint data and preset test task templates of the target system to construct an initial task dependency directed acyclic graph (DAG); S2, generating an initial scheduling instruction queue based on the initial task dependency DAG, executing probe tasks, and capturing the target system's response status data in real time; S3, constructing a defense situation awareness model and outputting the current defense activation state vector; S4, generating a reconstructed task execution graph based on the current defense activation state vector; S5, generating an adaptive scheduling instruction set based on the reconstructed task execution graph; and S6, completing penetration testing task coverage of the target system. By constructing a defense early warning model containing a long short-term memory network, this method effectively solves the problem that traditional tools are easily intercepted and blocked by WAF, IPS, and other devices due to packet sending patterns.
Need to check novelty before this filing date? Find Prior Art