Adaptive Sandbox Configuration via Endpoint Telemetry Correlation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current malware detection systems face challenges in configuring sandboxes to effectively analyze files, as there is no one-size-fits-all solution, especially for targeted files requiring a special environment, and malware programmers continually adapt to detection improvements.

Innovation Solution

A computer-implemented method and system that determines sandbox configurations by extracting elements from files, correlating them with endpoint properties, and generating sample-specific configurations using machine learning techniques to classify files as malicious or non-malicious, thereby identifying suitable sandbox environments for analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a standard sandbox configuration is used for all files, then the system is simple to operate, but targeted files requiring special environments cannot be properly analyzed

Engineering Contradiction:
Improvesandbox configuration adaptabilityVSAvoidsandbox configuration complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The sandbox configuration is made dynamic and adaptive rather than static. The system automatically adjusts sandbox parameters based on file characteristics and endpoint properties through machine learning models, allowing the configuration to evolve and adapt to different malware types and execution environments.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes multiple sandbox parameters simultaneously based on analyzed correlations, including but not limited to execution environment settings, system resource allocations, and software configurations. These parameter changes are driven by machine learning predictions of optimal configurations for detecting specific malware behaviors.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If sandbox configurations are customized for each file, then detection accuracy improves, but the time and resources required increase significantly

Engineering Contradiction:
Improvemalware detection accuracyVSAvoidconfiguration determination time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of file characteristics and endpoint properties before actual malware execution. Machine learning models pre-process and correlate this data to predict optimal sandbox configurations in advance, so that when a file needs analysis, the configuration is already determined and ready, minimizing delays.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates virtual copies of endpoint environments and sandbox configurations based on analyzed correlations, rather than physically setting up each unique configuration from scratch. These virtual copies can be rapidly instantiated and discarded, significantly reducing the time and resource overhead of customized configurations.

Inventive Principle:
Principle #26Copying

3Reliability

If traditional malware detection methods are used, then the system is easier to implement, but malware programmers can continually adapt and evade detection

Engineering Contradiction:
Improvemalware detection reliabilityVSAvoidmalware technique adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system implements continuous feedback loops where malware analysis results, detection outcomes, and endpoint behavior data are fed back into the machine learning models. This feedback enables the system to learn from new malware variants and detection successes/failures, continuously improving its ability to detect evolving threats while adapting to new malware techniques.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The machine learning models autonomously improve the detection system without requiring manual reconfiguration or expert intervention. The system self-adjusts by learning from accumulated data, automatically updating its understanding of malware behaviors and optimal detection strategies, making it resilient to continually adapting malware.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3602372B1Sample-specific sandbox configuration based on endpoint telemetry
Publication Date: 2024.05.22 CA TECH INC
  • EP3602372B1 patent drawingFigure 1
  • EP3602372B1 patent drawingFigure 2
  • EP3602372B1 patent drawingFigure 3

AI summary

A method for determining sandbox configurations for malware analysis is described. In one embodiment, the method may include receiving a plurality of files, extracting at least one element from at least one file from the plurality of files, identifying one or more properties associated with an endpoint, determining a correlation between the at least one extracted element and the one or more properties of the endpoint, and determining one or more sandbox configurations based at least in part on the determined correlation. In some cases, the endpoint is related to at least one of the plurality of files.