| CPC H04L 63/1416 (2013.01) [G06F 16/245 (2019.01); G06N 20/00 (2019.01); H04L 63/1441 (2013.01); H04L 2463/144 (2013.01)] | 19 Claims |

|
8. A method comprising:
receiving, by a computing device, a domain name system (DNS) query comprising a domain name;
determining, by a machine learning model, a plurality of features associated with the DNS query, wherein the plurality of features comprises at least a frequency of occurrence for each contiguous sequence of characters of a plurality of contiguous sequences of characters within a plurality of references and a ratio of vowels to consonants present within the domain name;
determining, based on the frequency of occurrence for each contiguous sequence of characters, a composite ranking for each contiguous sequence of characters present within the domain name, wherein the composite ranking is based at least in part on a plurality of rankings associated with the plurality of references;
determining, based on the ratio of vowels to consonants and the composite ranking, that the DNS query is associated with a malicious identifier generation algorithm; and
causing, based on the DNS query being associated with the malicious identifier generation algorithm, at least one remedial action to be performed.
|