UAB 360 IT (20240232353). MULTI-LEVEL MALWARE CLASSIFICATION MACHINE-LEARNING METHOD AND SYSTEM simplified abstract

From WikiPatents
Jump to navigation Jump to search

MULTI-LEVEL MALWARE CLASSIFICATION MACHINE-LEARNING METHOD AND SYSTEM

Organization Name

UAB 360 IT

Inventor(s)

Mantas Briliauskas of Vilnius (LT)

MULTI-LEVEL MALWARE CLASSIFICATION MACHINE-LEARNING METHOD AND SYSTEM - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240232353 titled 'MULTI-LEVEL MALWARE CLASSIFICATION MACHINE-LEARNING METHOD AND SYSTEM

Simplified Explanation:

This patent application describes a cyber security method and system for detecting malware using an anti-malware application that employs a fast locality-sensitive hashing evaluation with a vantage-point tree (VPT) structure to identify malicious and non-malicious files.

Key Features and Innovation:

  • Utilizes fast locality-sensitive hashing evaluation with a VPT structure for efficient malware detection.
  • Prioritizes high confidence identification of malicious and non-malicious files before deeper evaluation.
  • Provides a low confidence measure for files that are difficult to classify.

Potential Applications: The technology can be used in various industries such as cybersecurity, IT security, and data protection to enhance malware detection and prevention.

Problems Solved: Addresses the challenge of efficiently detecting and classifying malware files to improve overall cybersecurity measures.

Benefits:

  • Enhances the accuracy and speed of malware detection.
  • Helps in preventing security breaches and data loss.
  • Improves overall cybersecurity posture for organizations.

Commercial Applications: The technology can be applied in antivirus software, network security systems, and data protection tools to enhance malware detection capabilities and improve overall cybersecurity defenses.

Prior Art: Readers can explore prior research on locality-sensitive hashing, vantage-point trees, and malware detection algorithms to understand the background of this technology.

Frequently Updated Research: Stay updated on advancements in malware detection algorithms, cybersecurity technologies, and data protection methods to enhance the effectiveness of this innovation.

Questions about Malware Detection using Locality-Sensitive Hashing and VPT Structure: 1. How does the fast locality-sensitive hashing evaluation with a VPT structure improve malware detection efficiency? 2. What are the potential limitations of using a VPT structure for malware detection?


Original Abstract Submitted

a cyber security method and system for detecting malware via an anti-malware application employing a fast locality-sensitive hashing evaluation using a vantage-point tree (vpt) structure for the indication of malicious files and non-malicious files. the locality-sensitive hashing evaluation using the vpt structure can be performed prior to initiating the deeper, more computationally intensive evaluation and is used to identify with high confidence a scanned file or data object being (i) a malicious file, (ii) a non-malicious file, or a low confidence measure of the two.

Retrieved from "http://wikipatents.org/index.php?title=UAB_360_IT_(20240232353)._MULTI-LEVEL_MALWARE_CLASSIFICATION_MACHINE-LEARNING_METHOD_AND_SYSTEM_simplified_abstract&oldid=91117"