We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.
Feedback

Maschine Learning with Domain-Specific Ontology for IT Security Industry

Formal Metadata

Title
Maschine Learning with Domain-Specific Ontology for IT Security Industry
Alternative Title
ML with Domain-Specific Ontology for IT Security Industry
Title of Series
Number of Parts
60
Author
Contributors
License
CC Attribution 3.0 Unported:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
Identifiers
Publisher
Release Date2023
LanguageEnglish

Content Metadata

Subject Area
Genre
Abstract
The BSI monitors and assesses the current IT security situation and its long-term changes. This includes, for example, hacker groups or newly discovered security vulnerabilities. For this purpose, various news sources are monitored and important information is extracted to identify current trends and gain an overview. To optimize this process, we are working with the BSI to develop a system that supports the work by subjecting documents to automatic analysis using methods such as Named Entity Recognition (NER) and Named Entity Linking (NEL). While NER refers to the mapping of text passages to given classes through machine learning (e.g., "browser" to software), NEL aims at mapping to concrete entities of an ontology (e.g., "DOS" to "Disk Operating System"). We explain how we deal with the particular challenge of conceptual ambiguities ("DOS" stands not only for "Disk Operating System" but also for "Denial of Service"). The talk gives an insight into our entity recognition system and how we create a powerful tool for analyzing IT security documents by combining ontology and machine learning.