Social Safeguard, Inc.

Openq, Inc.

Otavio R Freire

Ruben Jimenez

Brian Christopher Carr

Matthew A Prentis

James P Zuffoletti

Embodiments of the present disclosure use natural language processing, machine learning and relevant corpora to detect social engineering attacks with a high degree of accuracy. In various embodiments, lexical features, spelling features and topical features are automatically analyzed from a source text and a model is employed to assess the likelihood that the source message is a social engineering attack.

System, device and method for detecting social engineering attacks in digital communications

In some embodiments, a non-transitory processor-readable medium includes code that causes a processor to receive, at a compliance device, a message from a source communication device addressed to a destination communication device. The code causes the processor to analyze at a context engine, the content of the message to determine a first risk level associated with a preference of an organization. The code further causes the processor to analyze at a regulatory engine, the content of the message to determine a second risk level associated with a regulatory standard of a specific industry and to define a composite risk level based on the first risk level and the second risk level. The code further causes the processor to send a notification to an administrator if the composite risk level satisfies a criterion, and to send the message to the destination communication device irrespective of the composite risk level.

Growing community of inventors

Charlottesville, VA, United States of America

Otavio R Freire