Google Inc.

Ca, Inc.

Adam Licata

Ashish Garg

James Paul Black

Adityashankar Kini

Alpesh Mote

Torry Campbell

Dwaipayan Dutta

A method for artificial intelligence-based automated parser creation includes obtaining a first event log of one or more first event logs of first telemetry data. The first event log includes one or more event log key-value pairs. The method includes generating, using a first artificial intelligence (AI) model, a portion of parser code to map a first event log key of an event log key-value pair of the one or more event log key-value pairs to a predefined field. The method includes generating an event log parser that includes the portion of the parser code. The method includes causing the event log parser to be executed on a second event log of one or more second event logs of second telemetry log data.

Artificial intelligence-based automated parser creation

Systems and methods include identifying fields associated with a log event of telemetry data and, for each field, selecting a key from multiple keys and generating a field-key mapping that includes a mapping from the fields to the selected key. The systems and methods generate an event log parser extension that includes the field-key mappings and validate the parser extension by testing its performance on sample log events. The systems and methods then execute a base parser and the validated event log parser extension on event logs to convert the event logs into a standardized format and perform data analytics on the standardized event logs to identify trends in the event logs and identify possible threats.

Augmenting parsers by added parser stages

The disclosed computer-implemented method for monitoring bait to protect users from security threats may include (i) monitoring a bait computing resource to detect attempts to access the bait computing resource, (ii) virtualizing the bait computing resource to prevent a false positive by hiding the bait computing resource from at least one trusted application that has been categorized as safe, (iii) detecting an attempt by a different application to access the virtualized bait computing resource, and (iv) performing a security action to protect a trusted user by reporting the attempt to access the virtualized bait computing resource by the different application. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods for monitoring bait to protect users from security threats

Growing community of inventors

South Orange, NJ, United States of America

Adam Licata