A fuzzy test case adaptive mutation method and device based on reinforcement learning
A technology of reinforcement learning and test cases, applied in the field of information security, it can solve the problems of blind mutation strategy, undesigned targeted mutation strategy, coarse granularity, etc., to achieve the effect of assisting loop feedback, improving intelligence, and improving efficiency and quality.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0031] The present invention will be described in detail below with reference to the accompanying drawings and examples.
[0032] The present invention provides a self-adaptive mutation scheme for fuzzy test cases based on reinforcement learning, the basic idea of which is: obtain the type of the test case to be mutated; select the mutation operation group corresponding to the type of the test case to be mutated; type information and each mutation The operation forms a context information, vectorizes to obtain the feature vector, and inputs the test cases to be mutated and the formed feature vectors into the single-step reinforcement learning model; the single-step reinforcement learning model transforms the selection problem of different mutation operations into a multi-armed bandit problem For the selection of different rockers, use the context-dependent confidence interval upper bound algorithm LinUCB to learn adaptive mutation operations to achieve adaptive learning of mu...
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