Amazon Technologies, Inc.

Michael Jerry Cervantez

Russell Leighton

Matthew R Evans

Sheila Mary Soulia

Requests to perform activity with respect to a customer account can be monitored to attempt to detect fraudulent activity due to compromised customer credentials or other unauthorized access. The unauthorized party can request actions such as to create a new account, mount a snapshot of customer data, and exfiltrate the customer data. Various embodiments monitor such requests and permissions granted to accounts not directly owned by a customer, and can apply automatic mitigations for suspicious activity in order to reduce the risk of exposing data to unauthorized accounts. Such an offering determines mitigations to perform, such as to block, alert, rate limit, or terminate the linked or non-linked account based on account reputation. The detection mechanism can use various heuristics to make mitigation decisions, as may consider factors such as account age, geolocation, access history, device fingerprint, network domain, payment type, prior suspicious activity, and the like.

Security policy enforcement

Data security may be automatically evaluated and adjusted using machine learning and/or satisfiability modulo theories (SMT). In various examples, a machine learning model(s) may be trained using training data that includes samples of customer data labeled with different types of data corresponding to different sensitivity levels of the samples of the customer data. Once trained, this trained machine learning model(s) can be used to classify data that is, or is requested to be, stored in a storage container. A SMT solver(s) may then evaluate the sufficiency of the existing data security (e.g., an existing access policy) of the storage container. Based on the result of the SMT solver's data security evaluation, an action(s) may be taken, such as a remedial action (e.g., adjusting data security of the storage container), a notification action (e.g., sending an alert about the data security deficiency), or the like.

Growing community of inventors

Fairfax Station, VA, United States of America

Michael Jerry Cervantez