Statistical Risk Scoring for Anti-Malware File Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional signature-based methods for detecting malware are ineffective against rapidly evolving threats, leading to high false positive rates and latency in file delivery, and electronic sandboxes are resource-intensive and can be evaded by attackers.

Innovation Solution

An anti-malware content data management system that calculates a risk assessment score for files based on historical statistics and configurable weighting factors, allowing for 'shades of grey' decision-making and optimizing sandbox usage by scoring files before sandbox processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If electronic sandbox is used to detect malicious code, then detection accuracy is improved, but processing time and resource overhead increase

Engineering Contradiction:
Improvemalware detection accuracyVSAvoidfile delivery latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by performing statistical analysis on file characteristics (metadata, headers, structure) before sandbox processing. This pre-screening identifies files with high probability of being benign based on historical data patterns, allowing them to bypass the time-consuming sandbox environment. The statistical model is trained in advance on labeled datasets, creating a ready-to-use classification system that reduces the need for full sandbox execution on every file.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent segments the file analysis process into two distinct stages: a fast statistical analysis stage that evaluates file characteristics against learned patterns, and a slow sandbox execution stage reserved for suspicious files. This segmentation allows the system to process most files quickly through the statistical filter while maintaining the ability to perform deep sandbox analysis on a small subset of high-risk files, thereby reducing overall latency.

Inventive Principle:
Principle #1Segmentation

2Reliability

If electronic sandbox is used to confine malicious code, then security isolation is improved, but system resource consumption increases

Engineering Contradiction:
Improvesecurity isolationVSAvoidsandbox maintenance overhead
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by using sandboxing selectively rather than universally. The statistical analysis model identifies files that do not require sandbox processing based on their characteristics matching benign patterns. Only files that score above a certain risk threshold are subjected to sandbox execution, meaning the resource-intensive isolation environment is activated only when partially necessary, reducing overall energy consumption while maintaining security for suspicious files.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If attackers delay malicious code activation until after sandbox inspection, then detection effectiveness decreases, but false positive rate increases

Engineering Contradiction:
Improvemalware detection effectivenessVSAvoidfalse positive identification
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent performs preliminary statistical analysis on file characteristics before sandbox execution, examining metadata, file headers, structure, and other static properties that are difficult for attackers to dynamically modify. This pre-inspection creates an additional layer of detection that occurs before the file enters the sandbox, making it harder for delayed-activation malware to evade detection since the statistical fingerprint is established before any code execution occurs.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3224755B1A statistical analytic method for the determination of the risk posed by file based content
Publication Date: 2020.11.04 GLASSWALL IP
  • EP3224755B1 patent drawingFigure 1
  • EP3224755B1 patent drawingFigure 2
  • EP3224755B1 patent drawingFigure 3

AI summary

A system and method for calculating a risk assessment for an electronic file is described. A database of checks, organized into categories, can be used to scan electronic files. The categories of checks can include weights assigned to them. An analyser can analyse electronic files using the checks. Issues identified by the analyser can be weighted using the weights to determine a risk assessment for the electronic file.