Automatically determining storage system data breaches using machine learning techniques
Methods, apparatus, and processor-readable storage media for automatically determining storage system data breaches using machine learning techniques are provided herein. An example computer-implemented method includes configuring a storage system by designating at least one storage object within the storage system for storing data identified as to be protected from breach; generating at least one multivariate data breach probability function using historical performance data of the designated storage object(s) and/or historical capacity data of the designated storage object(s); calculating at least one data breach score using the at least one multivariate data breach probability function, one or more machine learning techniques, and additional performance data of the designated storage object(s) and/or additional capacity data of the designated storage object(s); and performing one or more automated actions based at least in part on the at least one data breach score.
1. A computer-implemented method comprising:
configuring at least one storage system by designating at least one storage object within the at least one storage system for storing data identified as to be protected from breach;
generating at least one multivariate data breach probability function using at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object, wherein generating the at least one multivariate data breach probability function comprises determining one or more data access patterns, pertaining to one or more amounts of data accessed per one or more temporal periods, associated with the at least one designated storage object by processing the at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object;
calculating at least one data breach score using (i) the at least one multivariate data breach probability function, (ii) one or more machine learning techniques, and (iii) at least one of additional performance data of the at least one designated storage object and additional capacity data of the at least one designated storage object; and
performing one or more automated actions based at least in part on the at least one data breach score;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The computer-implemented method of claim 1 , wherein generating the at least one multivariate data breach probability function comprises processing the at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object using one or more beta distributions and one or more Poisson distributions.
3. The computer-implemented method of claim 1 , wherein using one or more machine learning techniques comprises using one or more machine learning-based Bayesian inference techniques.
4. The computer-implemented method of claim 1 , wherein using one or more machine learning techniques comprises using one or more machine learning-based Markov chain Monte Carlo algorithms.
5. The computer-implemented method of claim 1 , wherein generating the at least one multivariate data breach probability function comprises generating at least one probability density function.
6. The computer-implemented method of claim 1 , wherein performing the one or more automated actions comprises performing the at least one automated action upon a determination that the at least one data breach score exceeds a given threshold value.
7. The computer-implemented method of claim 1 , wherein performing the one or more automated actions comprises automatically configuring the at least one designated storage object to transition to an offline mode.
8. The computer-implemented method of claim 1 , wherein performing the one or more automated actions comprises selectively encrypting at least a portion of the data within the at least one designated storage object.
9. The computer-implemented method of claim 1 , wherein performing the one or more automated actions comprises automatically generating and outputting, to one or more storage administrator entities, at least one alert.
10. The computer-implemented method of claim 1 , further comprising:
updating the at least one multivariate data breach probability function using the at least one of additional performance data of the at least one designated storage object and additional capacity data of the at least one designated storage object.
11. The computer-implemented method of claim 1 , wherein calculating the at least one data breach score comprises calculating at least one data breach score upon obtaining at least one of new performance data of the at least one designated storage object and new capacity data of the at least one designated storage object.
12. The computer-implemented method of claim 1 , wherein the historical performance data comprises one or more of at least one central processing unit metric, at least one input-output operations per second metric, at least one latency metric, at least one metric pertaining to read operations, and at least one metric pertaining to write operations.
13. A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:
to configure at least one storage system by designating at least one storage object within the at least one storage system for storing data identified as to be protected from breach;
to generate at least one multivariate data breach probability function using at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object, wherein generating the at least one multivariate data breach probability function comprises determining one or more data access patterns, pertaining to one or more amounts of data accessed per one or more temporal periods, associated with the at least one designated storage object by processing the at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object;
to calculate at least one data breach score using (i) the at least one multivariate data breach probability function, (ii) one or more machine learning techniques, and (iii) at least one of additional performance data of the at least one designated storage object and additional capacity data of the at least one designated storage object; and
to perform one or more automated actions based at least in part on the at least one data breach score.
14. The non-transitory processor-readable storage medium of claim 13 , wherein generating the at least one multivariate data breach probability function comprises processing the at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object using one or more beta distributions and one or more Poisson distributions.
15. The non-transitory processor-readable storage medium of claim 13 , wherein using one or more machine learning techniques comprises using one or more machine learning-based Markov chain Monte Carlo algorithms.
16. The non-transitory processor-readable storage medium of claim 13 , wherein generating the at least one multivariate data breach probability function comprises generating at least one probability density function.
17. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to configure at least one storage system by designating at least one storage object within the at least one storage system for storing data identified as to be protected from breach;
to generate at least one multivariate data breach probability function using at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object, wherein generating the at least one multivariate data breach probability function comprises determining one or more data access patterns, pertaining to one or more amounts of data accessed per one or more temporal periods, associated with the at least one designated storage object by processing the at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object;
to calculate at least one data breach score using (i) the at least one multivariate data breach probability function, (ii) one or more machine learning techniques, and (iii) at least one of additional performance data of the at least one designated storage object and additional capacity data of the at least one designated storage object; and
to perform one or more automated actions based at least in part on the at least one data breach score.
18. The apparatus of claim 17 , wherein generating the at least one multivariate data breach probability function comprises processing the at least one of historical performance data of the at least one designated storage object and historical capacity data of the at least one designated storage object using one or more beta distributions and one or more Poisson distributions.
19. The apparatus of claim 17 , wherein using one or more machine learning techniques comprises using one or more machine learning-based Markov chain Monte Carlo algorithms.
20. The apparatus of claim 17 , wherein generating the at least one multivariate data breach probability function comprises generating at least one probability density function.