The present disclosure relates to a network-based centralized security monitoring (CSM) system. An example CSM includes one or more memory devices configured to store instructions thereon that, when executed by one or more processors, cause the one or more processors to receive a plurality of parameter data elements comprising one or more characters for a plurality of parameter types from a monitored site, determine for each of the plurality of parameter types a number of occurrences of a plurality of different character groups in the plurality of parameter data elements, generate a count structure indicating the number of occurrences of the plurality of different character groups in the plurality of parameter data elements for each of the plurality of parameter types, and generate a security signature for the monitored site, the security signature comprising the count structure for each of the plurality of parameter types.

Building security analysis system with site-independent signature generation for predictive security analysis

One embodiment provides a method, including: assigning a machine learning model signature to a machine learning model, wherein the machine learning model signature is generated using (i) data points and (ii) corresponding data labels from training data; receiving input comprising identification of a target machine learning model; acquiring a target signature for the target machine learning model by generating a signature for the target machine learning model using (i) data points from the assigned machine learning model signature and (ii) labels assigned to those data points by the target machine learning model; determining a stolen score by comparing the target signature to the machine learning model signature and identifying the number of data labels that match between the target signature and the machine learning model signature; and classifying the target machine learning model as stolen based upon the stolen score reaching a predetermined threshold.

Sankaranarayanan Karibik

Papers

Stolen machine learning model identification