US 12,443,754 B2
Automated data anonymization
Gyana Ranjan Dash, San Jose, CA (US); Antonio Nucci, San Jose, CA (US); Donald Mark Allen, Colorado Springs, CO (US); Kabeer Noorudeen, Artarmon (AU); Tatiana Alexandrovna Gaponova, Moscow (RU); and Konstantin Grechishchev, Moscow (RU)
Assigned to Cisco Technology, Inc., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on May 22, 2024, as Appl. No. 18/671,930.
Application 18/671,930 is a continuation of application No. 17/164,056, filed on Feb. 1, 2021, granted, now 12,026,280.
Application 17/164,056 is a continuation of application No. 15/964,876, filed on Apr. 27, 2018, granted, now 10,963,590, issued on Mar. 30, 2021.
Prior Publication US 2024/0311512 A1, Sep. 19, 2024
Int. Cl. G06F 7/04 (2006.01); G06F 21/60 (2013.01); G06F 21/62 (2013.01); H04L 41/0813 (2022.01)
CPC G06F 21/6254 (2013.01) [G06F 21/604 (2013.01); H04L 41/0813 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, from one or more networks, network telemetry data associated with the one or more networks;
receiving an indication that the network telemetry data is designated to be used as training data for a model;
based at least in part on the network telemetry data being designated to be used as training data, parsing the network telemetry data to identify a occurrences of a sequence of characters included in the network telemetry data;
identifying the occurrences of the sequence of characters as being of a sensitive information type;
replacing each of the occurrences of the sequence of characters with replacement characters that are in a format corresponding to the sequence of characters such that a structure of the network telemetry data is semantically maintained; and
subsequent to replacing each of the occurrences of the sequence of characters with the replacement characters, using the network telemetry data to train the model.