17454933. GENETIC PROGRAMMING FOR DYNAMIC CYBERSECURITY simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

GENETIC PROGRAMMING FOR DYNAMIC CYBERSECURITY

Organization Name

International Business Machines Corporation

Inventor(s)

Gary I. Givental of Bloomfield Hills MI (US)

Aankur Bhatia of Bethpage NY (US)

Joel Rajakumar of Atlanta GA (US)

GENETIC PROGRAMMING FOR DYNAMIC CYBERSECURITY - A simplified explanation of the abstract

This abstract first appeared for US patent application 17454933 titled 'GENETIC PROGRAMMING FOR DYNAMIC CYBERSECURITY

Simplified Explanation

The patent application describes techniques for enhancing cybersecurity using genetic programming and machine learning. Here are the key points:

  • The invention identifies subsets of features from a set of training security logs.
  • These feature subsets are modified using genetic programming techniques.
  • The modified feature subsets are scored using trained machine learning models called threat classifiers.
  • A set of feature subsets is selected based on their scores.
  • A type classifier is trained using the selected feature subsets, which is also a trained machine learning model.
  • The type classifier helps in classifying and identifying different types of cybersecurity threats.

Potential Applications

This technology can have various applications in the field of cybersecurity, including:

  • Enhancing the accuracy and effectiveness of threat detection systems.
  • Improving the identification and classification of different types of cybersecurity threats.
  • Strengthening the overall security posture of organizations by providing more robust cybersecurity measures.

Problems Solved

The techniques described in the patent application address the following problems in cybersecurity:

  • The need for more accurate and efficient threat detection methods.
  • The challenge of identifying and classifying different types of cybersecurity threats.
  • The requirement for advanced techniques to enhance the overall security of organizations.

Benefits

The use of genetic programming and machine learning in cybersecurity offers several benefits:

  • Improved accuracy in detecting and mitigating cybersecurity threats.
  • Enhanced efficiency in identifying and classifying different types of threats.
  • Increased resilience and robustness of cybersecurity systems.
  • Better protection of sensitive data and assets from cyber attacks.


Original Abstract Submitted

Techniques for improved cybersecurity are provided. A plurality of feature subsets are identified, each containing a respective subset of features from a plurality of features included in a set of training security logs. The plurality of feature subsets is modified using one or more genetic programming techniques, and each of the plurality of feature subsets is scored using a plurality of threat classifiers, where the plurality of threat classifiers comprise trained machine learning models. A set of feature subsets is selected, from the plurality of feature subsets, based on the scores. A type classifier is trained based on the set of feature subsets, where the type classifier comprises a trained machine learning model.

Retrieved from "http://wikipatents.org/index.php?title=17454933._GENETIC_PROGRAMMING_FOR_DYNAMIC_CYBERSECURITY_simplified_abstract_(International_Business_Machines_Corporation)&oldid=23533"