Roger Huffadine

Worcester

Innovator

Doomed to failure - why not use humans to spot Phishing?

Artificial Intelligence relies on the quality of the inference engine and the selection of data that is used to prime the system.

We already have e-mail filters that block my e-mails if I sign them Rxx [as in Roger xx] - These AI systems will be cracked in days by the people who write the phishing systems.

One simple way would be to pollute the AI system by feeding it a pre planned sequence of phishes over a period of several weeks that appear to follow a particular algorithm - but - that algorithm is specifically designed to produce a 'blind spot' in the AI knowledge. Its too easy to believe that criminals are stupid because the only criminals that we see are those who get caught.