Techniques of monitoring network traffic in a cloud computing environment
Machine learning techniques for updating a configuration of a computer network security system operating in a cloud computing environment. The techniques include obtaining a plurality of datasets containing information about a respective plurality of events detected by the computer network security system in the cloud computing environment; generating, using at least one trained ML model, a plurality of signatures representing the plurality of events, the generating comprising processing the plurality of datasets using the at least one trained ML model to obtain the plurality of signatures; clustering the plurality of signatures to obtain signature clusters representing clusters of events in the plurality of events; identifying a particular event cluster from among the clusters of events; and updating the configuration of the computer network security system based on characteristics of events in the identified particular event cluster.
1. A system for monitoring network traffic in a cloud computing environment, the system comprising:
at least a first computing device comprising a first set of one or more processors configured to execute a computer network security system, the computer network security system configured to perform:
detecting a plurality of events in the cloud computing environment,
generating a plurality of datasets containing information about at least some of the detected plurality of events, and
providing the plurality of datasets to a configuration generation and recommendation (CGR) system; and
at least a second computing device comprising a second set of one or more processors configured to execute the CGR system, the CGR system configured to perform:
obtaining the plurality of datasets from the computer network security system;
generating, using at least one trained ML model, a plurality of signatures representing the plurality of events, the generating comprising processing the plurality of datasets using the at least one trained ML model to obtain the plurality of signatures;
clustering the plurality of signatures to obtain signature clusters representing clusters of events in the plurality of events;
identifying a particular event cluster from among the clusters of events; and
updating the configuration of the computer network security system based on characteristics of events in the identified particular event cluster.
2. The system of claim 1 ,
wherein the computer network security system comprises a network traffic monitoring module comprising a plurality of event detection agents,
wherein different event detection agents are configured to detect events of different types, and
wherein events of different types correspond to network communications of different types of attacks on one or more software applications executing in the cloud computing environment.
3. The system of claim 1 , wherein the computer network security system comprises a firewall.
4. The system of claim 3 , wherein the firewall comprises a web application firewall (WAF) configured to monitor network traffic from and to one or more software applications executing in the cloud computing environment.
5. The system of claim 1 , wherein the computer network security system is further configured to perform:
identifying the at least some of the detected plurality of events, wherein the identifying comprises identifying events, from among the detected plurality of events, which present a security risk.
6. The system of claim 1 , wherein an event in the plurality of events may comprise one or more network communications of: a cross-site scripting (XSS) attack, a cross-site forgery attack, an HTTP redirect attack, a clickjacking attack, an XML external entity (XXE) attack, an account takeover (ATO) attack, a structured query language (SQL) injection attack, an operating system (OS) command injection attack, and/or a local file inclusion (LFI) attack.
7. The system of claim 1 , wherein the computer network security system and the CGR system execute in a common cloud computing environment.
8. The system of claim 1 , wherein the computer network security system and the CGR system execute in different cloud computing environments.
9. A method for monitoring network traffic in a cloud computing environment using a computer network security system, the method comprising:
using at least one computer hardware processor to perform:
detecting a plurality of events in the cloud computing environment,
generating a plurality of datasets containing information about at least some of the detected plurality of events;
generating, using at least one trained ML model, a plurality of signatures representing the plurality of events, the generating comprising processing the plurality of datasets using the at least one trained ML model to obtain the plurality of signatures;
clustering the plurality of signatures to obtain signature clusters representing clusters of events in the plurality of events;
identifying a particular event cluster from among the clusters of events; and
updating a configuration of the computer network security system based on characteristics of events in the identified particular event cluster.
10. The method of claim 9 ,
wherein the computer network security system comprises a network traffic monitoring module comprising a plurality of event detection agents,
wherein detecting the plurality of events comprises using different event detection agents to detect events of different types, and
wherein events of different types correspond to network communications of different types of attacks on one or more software applications executing in the cloud computing environment.
11. The method of claim 9 , wherein the method further comprises:
monitoring network traffic from and to one or more software applications executing in the cloud computing environment.
12. The method of claim 9 , wherein the method further comprises:
identifying the at least some of the detected plurality of events, wherein the identifying comprises identifying events, from among the detected plurality of events, which present a security risk.
13. The method of claim 9 , wherein an event in the plurality of events may comprise one or more network communications of: a cross-site scripting (XSS) attack, a cross-site forgery attack, an HTTP redirect attack, a clickjacking attack, an XML external entity (XXE) attack, an account takeover (ATO) attack, a structured query language (SQL) injection attack, an operating system (OS) command injection attack, and/or a local file inclusion (LFI) attack.
14. The method of claim 9 , wherein updating the configuration of the computer network security system, comprises:
generating, based on characteristics of events in the identified particular event cluster, one or more rules for processing events detected by the computer network security system in the cloud computing environment; and
updating the configuration of the computer network security system with the generated one or more rules.
15. The method of claim 9 ,
wherein the at least one trained ML model comprises a first trained ML model;
wherein the plurality of datasets comprises a first dataset comprising information about a first event in the plurality of events;
wherein generating the plurality of signatures comprises generating a first signature for the first event in the plurality of events; and
wherein generating the first signature comprises:
generating an initial numeric representation of the first dataset; and
providing the initial numeric representation as input to the first trained ML model to obtain the first signature, wherein the first signature is a lower-dimensional numeric representation than the initial numeric representation.
16. The method of claim 15 , wherein the first trained ML model is an autoencoder.
17. The method of claim 9 ,
wherein the plurality of events comprises a first event corresponding to a first type of attack, and a second event corresponding to a second type of attack different from the first type of attack;
wherein the at least one trained ML model comprises a first ML model for processing datasets for events corresponding to the first type of attack, and a second ML model for processing datasets for events corresponding to the second type of attack; and
generating the plurality of signatures comprises generating a first signature corresponding to the first event using the first ML model, and generating a second signature corresponding to the second event using the second ML model.
18. The method of claim 17 ,
wherein the plurality of datasets comprises a first dataset comprising information about the first event and a second dataset comprising information about the second event;
wherein generating plurality of signatures comprises:
generating a first initial numeric representation of the first dataset using a character embedding model, and providing the first initial numeric representation as input to the first ML model to obtain the first signature; and
generating a second initial numeric representation of the second dataset using the character embedding model, and providing the second initial numeric representation as input to the second ML model to obtain the second signature.
19. The method of claim 9 , further comprising:
monitoring network traffic from and to one or more software applications executing in the cloud computing environment using the computer network security system with the updated configuration.
20. At least one non-transitory computer-readable storage medium storing processor executable instructions that, when executed by at least one computer hardware processor cause the at least one computer hardware processor to perform a method for monitoring network traffic in a cloud computing environment using a computer network security system, the method comprising:
detecting a plurality of events in the cloud computing environment,
generating a plurality of datasets containing information about at least some of the detected plurality of events;
generating, using at least one trained ML model, a plurality of signatures representing the plurality of events, the generating comprising processing the plurality of datasets using the at least one trained ML model to obtain the plurality of signatures;
clustering the plurality of signatures to obtain signature clusters representing clusters of events in the plurality of events;
identifying a particular event cluster from among the clusters of events; and
updating a configuration of the computer network security system based on characteristics of events in the identified particular event cluster.