Implementation of Token Parsing Technique for Regex Based Classification of Unstructured Data for Cyber Threat Analysis
| Autor: | Mohd Ezanee Rusli, Azril Azam Abdul Rahim, Norziana Jamil, Muhammad Hazim Mohd Pakhari |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Parsing
Information retrieval Computer science 020206 networking & telecommunications Unstructured data Timeline 02 engineering and technology Plan (drawing) computer.software_genre Security token Countermeasure Threat model 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing computer Cyber threats |
| Zdroj: | 2020 8th International Conference on Information Technology and Multimedia (ICIMU). |
| DOI: | 10.1109/icimu49871.2020.9243415 |
| Popis: | Cyber Threat Intelligence (CTI) is a concept for information about cyber threats which were analysed, structured, and refined. This information is used to help organizations to understand the current risk that have different levels that might bring harm to their enterprises. Besides, CTI can also help organizations to plan for defensive countermeasures and protect themselves from the attacks that can cause them damage. In this paper, we introduce a token parsing technique for regex based classification of unstructured data for cyber threat analytic (CTA) engine that does threat analysis based on data crawled from several public resources. Our engine crawls and fetch data from the public resource in time series, analyse the data and provide a meaningful information to the user with the timeline of the fetched parameter. The collected data which appears as non-structured are converted by the engine to appear as a structured data and then be inserted into the database. Subsequently, the engine then analyses the threat data by modelling it before useful information be returned to the user. The challenge is to have a structured data useful for analysis. This paper explains how our token parsing technique is useful in regex based classification to convert the unstructured data into useful structured data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|