Current security and access control technologies permit controlling authorization and authentication based on network addresses. However, such technologies do not address problems resulting from administrator error and oversight. Inadvertent mistakes and/or oversight can result in cloud resources being erroneously exposed to external access by malicious actors. This disclosure describes the application of a trained machine learning model to determine a credibility score for the source IP address of a request received at a cloud resource. The outcome of the credibility evaluation is used to enact access controls for the corresponding source IP address.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.