Intent-based approach leverages neural networks to deliver targeted classifications to BECs


According to Cisco Talos researchers, the system catches BEC messages using the intent-based approach regardless of whether a threat actor poses as a C-level executive or any other type of rank-and-file employee within the firm.

This method extracts text from emails and transforms sentences into numeric vectors by encoding the meaning of the words in the sentences using neural network language model (NNLM) or bi-directional encoder representations from transformers (BERT) encodings. Then, deep neural networks are used to carry out detection and classification. Read More…