Abstract:
As we continue to see a rise in the number and severity of cyber attacks, we simultaneously have seen an explosion of progress in the field of artificial intelligence, and specifically machine learning. Machine learning is a sub-field of AI which thrives on the availability of data. With a sufficient amount of data, for example a large number of emails with phishing attempts, we can train an algorithm to be able to recognize a new phishing attempt as malicious. Naturally, with the growing problems in cybersecurity and the growing efficacy of machine learning algorithms which can make predictions from complex data, there has been interest in applying machine learning to security. This article gives a broad, non-technical overview of the categories of machine learning algorithms: supervised versus unsupervised learning. They talk about an email spam filter and network flow data as examples of using machine learning for better security. This article is part of a series which explores uses of machine learning, some of which are more specific areas of cybersecurity.
Keywords
Machine learning, ransomware, big data
Institution:
Carnegie Mellon University