Assertion-oriented vulnerability detection method fusing large model semantic reasoning

By constructing a program dependency graph for guided slicing and generating path constraints through large-scale model semantic reasoning, and combining symbolic execution and verifier feedback, the problem of low efficiency, high false positives, and high false negatives in existing assertion detection technologies is solved, achieving high accuracy and interpretable vulnerability detection.

CN122113112APending Publication Date: 2026-05-29GUANGZHOU INSTITUTE OF TECHNOLOY XIDIAN UNIVERSITY +1
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
GUANGZHOU INSTITUTE OF TECHNOLOY XIDIAN UNIVERSITY
Filing Date
2026-01-20
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing software vulnerability detection methods suffer from problems such as low efficiency, high false positive rate, high false negative rate, logical inconsistency, and unverifiableness when dealing with assertion-related defects. In particular, they are difficult to accurately extract key execution paths and generate logically consistent precondition constraints in assertion failure detection tasks.

Method used

By constructing a dependency graph of the program for guided slicing, an assertion-related slice graph is generated. The path constraints with the weakest preconditions are generated using large model semantic reasoning and embedded in symbolic execution for verification. Combined with the verifier feedback mechanism, corrections and re-reasoning are performed to ensure the logical consistency and verifiability of the path constraints.

Benefits of technology

It achieves high accuracy, interpretability, and verifiability in assertion-related vulnerability detection, significantly reducing false positive and false negative rates, improving detection efficiency and recall, and ensuring the credibility and interpretability of detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122113112A_ABST
    Figure CN122113112A_ABST
Patent Text Reader

Abstract

The application provides an assertion-oriented vulnerability detection method fusing a large model semantic reasoning, a dependency graph is constructed according to control and data dependency relationships and statements of an assertion, a slice graph related to the assertion is obtained by performing directional slicing according to the dependency graph, and path decomposition is performed on the slice graph to generate a key execution path; the key execution path is reasoned forward from an assertion failure condition according to a weakest precondition norm to obtain a target path constraint capable of triggering the assertion; the target path constraint is embedded in symbolic execution for solving and satisfaction verification is performed according to a solving process, and constraint generation is modified and re-reasoned according to a verification result; only control dependency and data dependency related to the assertion are reserved, and the path explosion problem of symbolic execution is solved; a path condition with semantic consistency is generated to avoid a semantic sensitivity problem; a semantic conclusion is mapped into a formal logic expression to ensure verifiability of a logical constraint; and the effect of explainability, verifiability and high accuracy is achieved.
Need to check novelty before this filing date? Find Prior Art