[Python Artificial Intelligence] 40. Named Entity Recognition (1) Detailed explanation of threat intelligence entity recognition based on BiLSTM-CRF

Starting from this column, the author formally studies Python deep learning, neural networks and artificial intelligence related knowledge. The previous article popularized the Keras deep learning environment configured in VS Code, compared common deep learning frameworks, and finally popularized handwritten digit recognition cases. This article will explain how to implement threat intelligence entity identification and use the BiLSTM-CRF algorithm to extract ATT&CK-related technical and tactical entities, which is an important support for the construction of security knowledge graphs. Basic article, I hope it will be helpful to you!

Version Information:

• keras-contrib V2.0.8
• keras V2.3.1
• tensorflow V2.2.0

Common frameworks are shown below:

• https://aclanthology.org/2021.acl-short.4/