Polymorphic Malware Detection via Metadata Clustering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Polymorphic malware poses a significant challenge for anti-virus systems as it can be packed in different ways, generating unique hash values that are difficult to detect using traditional static signature-based methods, making it hard for anti-virus applications to identify and prioritize for analysis.

Innovation Solution

A server-based method that receives hash values and metadata from client devices, clusters similar metadata, and determines if a file is likely polymorphic by comparing received data with stored records, generating fingerprints based on metadata to identify and prioritize potentially malicious files for further analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional static signature-based methods are used to detect malware, then simple and fast detection is achieved, but polymorphic malware with unique hash values cannot be effectively detected

Engineering Contradiction:
Improvedetection capabilityVSAvoiddetection difficulty
Core Design Contradiction:
ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent transitions from single-dimension hash-based detection to multi-dimensional detection by incorporating metadata clustering. Instead of relying solely on hash values, the system analyzes metadata patterns (file characteristics, behavior, structure) to identify polymorphic malware, adding a new dimension to the detection approach that enables reliable identification of uniquely hashed malicious files.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent introduces metadata as an intermediary element between the malware file and the detection system. By analyzing metadata patterns and clustering similar files, the system creates a mediator that helps identify polymorphic malware without directly analyzing the unique hash values, thereby overcoming the detection difficulty while maintaining reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If polymorphic malware is packed in different ways to generate unique hash values, then evasion of detection is improved, but identification and prioritization for analysis becomes difficult

Engineering Contradiction:
Improvemalware adaptabilityVSAvoidanalysis prioritization efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements a feedback mechanism where metadata from analyzed files is clustered and stored for future reference. When new files are encountered, their metadata is compared against existing clusters to identify patterns and prioritize analysis. This feedback loop enables the system to adapt to polymorphic malware variations while maintaining efficient prioritization based on historical data.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent changes the detection parameters from static hash values to dynamic metadata patterns. By analyzing multiple metadata parameters (file structure, behavior, characteristics) and clustering them, the system can identify polymorphic malware variants and prioritize them for analysis based on metadata similarity rather than unique hashes, thereby maintaining productivity despite malware adaptability.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If client/server model is used with centralized database, then global malware situation analysis is improved, but data transmission and processing requirements increase

Engineering Contradiction:
Improveglobal analysis capabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts only the necessary metadata information from file analysis and transmits it to the server for clustering and global analysis. Instead of transferring complete file data, the system extracts and sends only the relevant metadata patterns, reducing data transmission requirements while maintaining the ability to perform comprehensive global malware analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the detection system into client-side file analysis and server-side metadata clustering. By dividing the complex task into separate modules, each handling specific functions (local file scanning vs. global pattern matching), the system reduces overall complexity while enabling reliable global malware situation analysis through coordinated operation of segmented components.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP2593893B1Identifying polymorphic malware
Publication Date: 2016.11.16 F SECURE CORP
  • EP2593893B1 patent drawingFigure 1~2
  • EP2593893B1 patent drawingFigure 3~4
  • EP2593893B1 patent drawingFigure 5

AI summary

A method and apparatus for identifying an electronic file as polymorphic malware. A server receives from a client device a hash value and metadata associated with an electronic file. The server determines that the received metadata relates to corresponding metadata stored at a database, the corresponding stored metadata being associated with a further hash value that differs from the received hash value. A determination is made that each of the received hash values have been reported by fewer than a predetermined number of clients and, as a result, it is determined that the electronic file is likely to be polymorphic malware.