Information regarding cyber threats can be obtained from a large variety of information security data sources. However, it is a time-consuming task for security experts to extract the needed information on indicators of compromise (such as malicious IP addresses, file hashes, user names or any other traces that may be observed during an attack) or potential countermeasures against an attacker. The goal of this bachelor's thesis is to overcome this issue by implementing a prototype that automatically extracts the needed information and provides it in machine-readable format for further processing.
(Note: The bar chart shows the estimated distribution of tasks.)
Literature Study on the State-of-the-Art
Natural Language Processing
Implementation of the Prototype
Evaluation of the Protoype