What is it about?
CASIE is an AI system that extracts key information about cybersecurity events from a document such as a news story or security document. It uses the information to create entries in a knowledge graph describing the cybersecurity events. The system was trained with human annotations on 1000 news articles. CASIE uses several deep neural network approaches with attention and incorporates rich linguistic features and word embeddings. An evaluation of the results shows that it works well.
Featured Image
Photo by Mel Poole on Unsplash
Why is it important?
Hackers are always finding new ways to attack networks and computing systems. Our systems that protect them need information on the latest techniques being used to protect systems better.
Read the Original
This page is a summary of: CASIE: Extracting Cybersecurity Event Information from Text, Proceedings of the AAAI Conference on Artificial Intelligence, April 2020, Association for the Advancement of Artificial Intelligence (AAAI),
DOI: 10.1609/aaai.v34i05.6401.
You can read the full text:
Contributors
The following have contributed to this page
