AWS unveils a monster security system to keep it safe from threats


Amazon Web Services (AWS) has unveiled a new large-scale security system designed to keep its cloud services secure.
The Mithra system uses an internal neural network graph model with 3.5 billion nodes and 48 billion edges to spot and rank the trustworthiness of domains and identify potential threats.
Considering a single AWS region can see up to 200 trillion DNS requests in one day, the size of this monster security system is no surprise, and it can detect 182,000 new malicious domains per day.
Monster Mithra
Once Mithra identifies a domain queried within AWS, it will assign it a trustworthiness score, removing the need to rely on third parties. Not only does this remove potential supply chain threats, it also helps AWS maintain a high-quality list of malicious domains to observe, and therefore observe cybercriminal behavior.
The massive neural network graph (which AWS says could be one of the largest in existence) detects malicious domains with a high level of accuracy, and can even predict malicious domains days, weeks and months before they appear on the threat feeds of third party security providers.
Mithra can therefore provide a constantly updated list of malicious domain names for security providers to monitor and block. The list can also be supplied to third party threat feeds in order to reduce false positives, and Mithra’s detection of millions of security events per day can be used by AWS security analysts for investigations and additional context.
The notifications provided by Mithra to organizations of a potential cyber attack from a malicious domain include recommendations on response, such as checking security logs for activity from specific domains and blocking them, and moving infrastructure behind a firewall.
Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
“We are encouraged by how our efforts to share our threat intelligence have helped customers and other organizations be more secure, and we are committed to finding even more ways to help,” Amazon Chief Information Security Officer CJ Moses said in a blog post announcing the launch.
More from TechRadar Pro
Amazon Web Services (AWS) has unveiled a new large-scale security system designed to keep its cloud services secure. The Mithra system uses an internal neural network graph model with 3.5 billion nodes and 48 billion edges to spot and rank the trustworthiness of domains and identify potential threats. Considering a…
Recent Posts
- Balatro has had its PEGI 18 age rating overturned following appeal: ‘I hope this change will allow developers to create without being unfairly punished’
- Three years later, the Steam Deck has dominated handheld PC gaming
- Google Gemini’s AI coding tool is now free for individual users
- Attention, Kindle owners –today is your last chance to download backups of your ebooks
- Scooby-Doo is a good movie with a bad Rotten Tomatoes score – here’s why you should ignore the critics and watch it before it leaves Netflix
Archives
- February 2025
- January 2025
- December 2024
- November 2024
- October 2024
- September 2024
- August 2024
- July 2024
- June 2024
- May 2024
- April 2024
- March 2024
- February 2024
- January 2024
- December 2023
- November 2023
- October 2023
- September 2023
- August 2023
- July 2023
- June 2023
- May 2023
- April 2023
- March 2023
- February 2023
- January 2023
- December 2022
- November 2022
- October 2022
- September 2022
- August 2022
- July 2022
- June 2022
- May 2022
- April 2022
- March 2022
- February 2022
- January 2022
- December 2021
- November 2021
- October 2021
- September 2021
- August 2021
- July 2021
- June 2021
- May 2021
- April 2021
- March 2021
- February 2021
- January 2021
- December 2020
- November 2020
- October 2020
- September 2020
- August 2020
- July 2020
- June 2020
- May 2020
- April 2020
- March 2020
- February 2020
- January 2020
- December 2019
- November 2019
- September 2018
- October 2017
- December 2011
- August 2010