A search enhancement-based SQL injection adversarial sample generation method

By constructing a knowledge base of SQL injection adversarial examples and using a large language model collaborative generation technique, the robustness and diversity issues of SQL injection attacks in existing technologies are solved, achieving efficient generation and training and improving the defense capabilities of the detection model.

CN122660993APending Publication Date: 2026-08-28联通西部创新研究院有限公司
0 Cites 0 Cited by

Patent Information

Application Number
CN202610965100.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-06-30
Publication Date
2026-08-28

AI Technical Summary

Technical Problem

Existing malicious traffic detection methods are not robust to complex SQL injection attacks, lack diversity and semantic consistency in the generated adversarial samples, and lack effective utilization of historical attack samples, resulting in insufficient adaptability and recognition ability of the models in real-world environments.

Method used

We construct a knowledge base of SQL injection adversarial examples, combine a large language model and retrieval enhancement techniques to generate highly concealed and diverse adversarial examples, and improve the robustness of the detection model through adversarial training.

Benefits of technology

It significantly improves the quality and efficiency of adversarial sample generation, enhances the detection model's ability to identify unknown attacks and its defense robustness, and achieves effective defense against complex SQL injection attacks.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a kind of based on search enhancement SQL injection counter sample generation method, belong to traffic analysis and network security technical field.The application is divided into two links, first collect multiple sets of public traffic data set extraction SQL injection load, generate counter sample by a variety of variation mode, after structured cleaning, vectorization process builds SQL injection counter sample knowledge base.Second, rely on search enhancement generation technology, search similar sample and variation strategy in knowledge base, guide large language model iteration generates new counter sample, and effective sample is supplemented to knowledge base.Finally, normal traffic, original malicious sample and new counter sample are fused to construct training set, and the adversarial training of traffic detection model is completed.The application can improve the diversity and generation efficiency of counter sample, effectively strengthen the recognition ability and overall robustness of detection model to SQL injection variation attack.
Need to check novelty before this filing date? Find Prior Art