Generative AI Configuration Correction for Infrastructure Compliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current infrastructure-as-code (IAC) management systems require manual intervention to address security vulnerabilities and compliance issues detected by SAST and DAST tools, which is time-consuming and prone to errors, especially when adapting to tool updates or replacements.
Innovation Solution
A process utilizing a generative artificial intelligence model to automatically generate correction recommendations for configuration files in IT environments, by analyzing execution reports and context information, and validating these recommendations using a similarity measure before submitting them for user evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual correction of configuration files is performed based on SAST and DAST tool recommendations, then security vulnerabilities can be addressed, but the process becomes time-consuming and tedious
Solution Approach 1:
The system enables self-service by automatically generating correction recommendations using a generative AI model that processes SAST and DAST execution reports. The model autonomously analyzes security anomalies and produces corrected configuration code without requiring manual intervention, thereby reducing correction time while maintaining security reliability.
Solution Approach 2:
The patent replaces the mechanical manual process of reviewing and correcting security vulnerabilities with an automated intelligent system. The generative AI model substitutes human analysts by processing execution reports and generating corrections algorithmically, eliminating the time-consuming manual mechanics of vulnerability assessment and patching.
2Reliability
If multiple SAST and DAST tools are used to detect security anomalies, then comprehensive security coverage is achieved, but adapting to tool updates and replacements becomes complex and time-consuming
Solution Approach 1:
The generative AI model serves as a universal processor that handles execution reports from multiple different SAST and DAST tools through a standardized interface. The model can process various tool formats and anomaly types uniformly, providing multi-functional capability that maintains security coverage while adapting to different tools without requiring separate handling procedures for each tool update or replacement.
Solution Approach 2:
The AI model acts as an intermediary layer between diverse SAST and DAST tools and the configuration correction process. This mediator standardizes the interaction by accepting various tool formats and converting them into a unified processing format, thereby decoupling the system from specific tool implementations and simplifying adaptation to tool updates or replacements.
3Manufacturing precision
If comprehensive context information is provided to the AI model for accurate correction recommendations, then recommendation quality improves, but processing time and computational resources increase
Solution Approach 1:
The system extracts only the essential and relevant context information from execution reports needed for generating accurate corrections. By selectively extracting critical anomaly details and configuration contexts rather than processing all available information, the model maintains high recommendation accuracy while reducing unnecessary processing time and computational overhead.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a method and device for generating a recommendation to correct a configuration file of an infrastructure within a computer environment in which services are run, said infrastructure having been automatically deployed from said configuration file, comprising: 16. Obtaining (E1) an execution report including a conformity anomaly detected in the configuration file during the execution of said service; 17. Presenting (E5) a request to correct the anomaly as input to a previously trained generative artificial intelligence model, and obtaining (E6) as output a recommendation to correct the configuration file; 18. Validating (E7) the recommendation to correct the configuration file including determining a similarity measure with respect to said context information and comparing it to an acceptability threshold; 19.When the similarity measure is validated, the (E8) recommendation to correct the configuration file is submitted for evaluation by a user.