Systems and methods for DNS text classification
A computerized method is disclosed that includes operations of training a machine learning model using a labeled training set of data, wherein the machine learning model is configured to classify domain name server (DNS) records, obtaining DNS record data including at least a first DNS Txt record, applying the trained machine learning model to the first DNS Txt record to classify the first DNS Txt record and responsive to the classification of the first DNS Txt record, generating a flag for a system administrator. The trained machine learning model may classify the first DNS Txt record using logistic regression. In some instances, applying the trained machine learning model to the first DNS Txt record includes performing a tokenizing operation on the first DNS Txt record to generate a tokenized first DNS Txt record.
1. A computerized method comprising:
accessing an initial set of data from a data store, the initial set of data comprises domain name server (DNS) record data including one or more historic DNS records that include text data and that represent one or more transmissions of data between a source device and a domain name server;
preparing a labeled training set of data from the initial set of data prior to training a machine learning model by providing labels for one or more DNS records within the initial set of data;
training the machine learning model using the labeled training set of data, wherein the machine learning model is configured to classify DNS records;
obtaining DNS record data including at least a first DNS Txt record;
applying the trained machine learning model to the first DNS Txt record to the first DNS Txt record; and
responsive to the classification of the first DNS Txt record, generating a flag for a system administrator.
2. The computerized method of claim 1 , wherein the labels include benign and unknown.
3. The computerized method of claim 1 , wherein providing the labels includes applying a set of regular expressions to text of the one or more DNS records within the initial set of data.
4. The computerized method of claim 1 , wherein the DNS record data is streaming data.
5. The computerized method of claim 1 , wherein the trained machine learning model classifies the first DNS Txt record using logistic regression.
6. The computerized method of claim 1 , wherein when the first DNS Txt record is classified as benign, applying the trained machine learning model to the first DNS Txt record further results in classification within one of a predetermined category set including at least email, verification, encoded text or pattern.
7. The computerized method of claim 1 , wherein applying the trained machine learning model to the first DNS Txt record includes performing a tokenizing operation on the first DNS Txt record to generate a tokenized first DNS Txt record.
8. A computing device, comprising:
a processor; and
a non-transitory computer-readable medium having stored thereon instructions that, when executed by the processor, cause the processor to perform operations including:
accessing an initial set of data from a data store, the initial set of data comprises domain name server (DNS) record data including one or more historic DNS records that include text data representing one or more transmissions of data between a source device and a domain name server;
preparing a labeled training set of data from the initial set of data prior to training a machine learning model by providing labels for one or more DNS records within the initial set of data;
training the machine learning model using the labeled training set of data, wherein the machine learning model is configured to classify DNS records,
obtaining DNS record data including at least a first DNS Txt record,
applying the trained machine learning model to the first DNS Txt record to the first DNS Txt record, and
responsive to the classification of the first DNS Txt record, generating an alert for a system administrator.
9. The computing device of claim 8 , wherein the labels include benign and unknown.
10. The computing device of claim 8 , wherein providing the labels includes applying a set of regular expressions to text of the one or more DNS records within the initial set of data.
11. The computing device of claim 8 , wherein the DNS record data is streaming DNS record data.
12. The computing device of claim 8 , wherein the trained machine learning model classifies the first DNS Txt record using logistic regression.
13. The computing device of claim 8 , wherein when the first DNS Txt record is classified as benign, applying the trained machine learning model to the first DNS Txt record further results in classification within one of a predetermined category set including at least email, verification, encoded text or pattern.
14. The computing device of claim 8 , wherein applying the trained machine learning model to the first DNS Txt record includes performing a tokenizing operation on the first DNS Txt record to generate a tokenized first DNS Txt record.
15. A non-transitory computer-readable medium having stored thereon instructions that, when executed by one or more processors, cause the one or more processors to perform operations including:
accessing an initial set of data from a data store, the initial set of data comprises domain name server (DNS) record data including one or more historic DNS records that include text data and that represent one or more transmissions of data between a source device and a domain name server;
preparing a labeled training set of data from the initial set of data prior to training a machine learning model by providing labels for one or more DNS records within the initial set of data;
training the machine learning model using the labeled training set of data, wherein the machine learning model is configured to classify domain name server (DNS) records;
obtaining DNS record data including at least a first DNS Txt record;
applying the trained machine learning model to the first DNS Txt record to generate a classificatoin of the first DNS Txt record, and
responsive to the classification of the first DNS Txt record, generating a flag for a system administrator.
16. The non-transitory computer-readable medium of claim 15 , wherein the labels include benign and unknown.
17. The non-transitory computer-readable medium of claim 15 , wherein providing the labels includes applying a set of regular expressions to the text of the one or more DNS records within the initial set of data.
18. The non-transitory computer-readable medium of claim 15 , wherein the DNS record data is streaming DNS record data.
19. The non-transitory computer-readable medium of claim 15 , wherein the trained machine learning model classifies the first DNS Txt record using logistic regression.
20. The non-transitory computer-readable medium of claim 15 , wherein applying the trained machine learning model to the first DNS Txt record includes performing a tokenizing operation on the first DNS Txt record to generate a tokenized first DNS Txt record.