Amazon’s Macie Makes Use of Artificial Intelligence for Security of Data


Published Date : Aug 22, 2017

Artificial intelligence is now being blended with cloud storage so as to help customers secure their data. Who is behind this? Amazon! The company has become the first cloud provider to have implemented this and the new service is called Amazon Macie, relying on machine learning to discover, protect, and classify sensitive data automatically that is stored in AWS. The main objective of Amazon’s Macie is to find and report all the sensitive data which is stored in the cloud that is not secure fully. Macie analyzes the usage and access patterns and when it discovers that a new user from an unusual IP Address is accessing document, it alerts the customers.

AWS is taking the fullest advantage of the various supervised and unsupervised machine learning algorithms in order to make Macie smart and intelligent. Macie makes use of Natural Language Processing (NLP) for data parsing which is stored in documents and identifies patterns such as social security numbers, SSH keys, passwords, credit card numbers, API keys, emails, or any other sensitive data. Macie then classifies documents into one of the predefined risk levels based on the criticality and sensitivity of the data discovered. It then starts monitoring how this high risk data is being accessed and applied AI for understanding the past data access patterns and assesses the activity of applications, users, and service accounts, automatically. Thus, any unauthorized access can be detected and data leaks can be avoided.