Machine Learning-Powered Amazon Detective Exits

After being available in preview since December, the Amazon Detective managed security service was made generally available this week.
Amazon Detective was first announced at the 2019 re-Invent conference. It uses machine learning to investigate security incidents across a user’s entire Amazon Web Services environment. It pulls information from multiple AWS data storages, such as AWS CloudTrail and AWS GuardDuty, and creates visualizations that show specific security events’ origins and consequences.
Amazon Detective is different from other AWS services such as Macie or GuardDuty, which simply identify security flaws and send alerts. Amazon Detective is intended for situations where it’s necessary “large quantities AWS log data to determine cause and effect of a security problem,” said Sebastien Stormacq (AWS developer evangelist), in a blog post Tuesday.
These situations usually require scripting, the use ETL and SIEM tools, as well as proficiency in data science to organize, contextualize, and contextualize all relevant information. Stormacq explained that Amazon Detective automates this process.
“Amazon Detective uses machine-learning models to produce graphical representations about your account behavior. It helps you answer questions such as “Is this an unusual API request for this role?” Or, “Is this expected spike in traffic from this instance?” He wrote. “You don’t need to code to configure or tune your own queries.
Amazon Detective can be run across up to 1,000 AWS accounts. This gives users a complete view of their cloud environment. Data visualizations can be saved for up to one calendar year. This is useful for monitoring log behavior over time.
Amazon Detective is available in these 14 areas:
US East (Ohio).
, US East (N. Virginia)
, US West (N. California).
, US West (Oregon)
, Asia Pacific (Seoul).
, Asia Pacific (Singapore)
Asia Pacific (Sydney).
, Asia Pacific (Tokyo).
, Europe (Frankfurt).
, Europe (Ireland).
, Europe (London).
, Europe (Paris).
, Canada (Central)
, and South America (Sao Paulo).
. More information is available here.

Machine Learning-Powered Amazon Detective Exits
Scroll to top