Can artificial intelligence spot spam quicker than humans?

This article discusses the modern era of technology in which artificial intelligence and machine learning techniques are utilized to help filter spam mails. It was only within the last few decades that the first computer, IBM’s Deep Blue, was able to defeat a human chess grandmaster, a feat that signaled a new era of technology and computing power. With regard to spam filters, these algorithms are trained using large datasets of emails, as well as live user feedback, allows the algorithm to improve and better filter the mail going through your inbox. It is interesting to note, however, that 75% of emails that people report as spam are actually “legitimate”—i.e. they are newsletters, offers, notifications, digests that people once subscribed to but perhaps are no longer interested in. While the trained algorithms are able to filter out the majority of spam emails, there are still limitations to artificial intelligence. Moreover, since hackers are also able to use AI and ML, it is crucial to still have humans to step in and check the processes at various junctures. It is moments like these where humans still have the advantage over computers. As Oetjen explains, “The human brain nevertheless does have a unique advantage over this artificial brain power — it can solve a problem that it has never seen before. Nothing in machine learning is like that. Everything it does has been designed to deal with a specific problem. Its mastery of any particular task is not transferable.”