Cyber security system applying network sequence prediction using transformers
A cyber threat defense system and a method for detecting a cyber threat may use a predictor, e.g. a Transformer deep learning model, which is configured to predict a next item in the sequence of events and to detect one or more anomalies in the sequence of events. This provides a notification comprising (i) information about the one or more anomalies; and (ii) a prediction of what would have been expected.
1. A cyber threat defense system, the cyber threat defense system comprising:
an analyzer module comprising a modeler to model network data as a sequence of events, and a predictor to predict a next item in the sequence of events and to identify one or more anomalies in the sequence of events;
a user interface configured to convey a notification of one or more anomalies occurring in a network protected by the cyber threat defense system; and
an autonomous response module configured to generate at least a notification in response to the analyzer module identifying the one or more anomalies;
wherein the predictor is configured to provide in the notification conveyed on the user interface (i) information about the one or more anomalies, and ii) additional contextual information, beyond a possible score, about the one or more anomalies in order to enhance a user's understanding regarding the identified one or more anomalies, where the predictor is configured to use a JA3 hash of the network data and a domain to match to particular user agents; and to provide in the notification information about the particular user agents.
2. The cyber threat defense system according to claim 1 , wherein the autonomous response module is configured to generate at least the notification to a user in response to detected one or more anomalies above a first threshold level and/or configured to generate an autonomous response to mitigate a cyber threat when the detected one or more anomalies are indicative above a second threshold level.
3. The cyber threat defense system according to claim 1 , wherein the predictor is a Transformer deep learning model.
4. The cyber threat defense system according to claim 1 , wherein the additional contextual information identifies each anomalous part of an event in the sequence of events.
5. The cyber threat defense system according to claim 1 , wherein the additional contextual information identifies a plurality of anomalies in parts of an event in a sequence of events, when multiple anomalies were detected with the identified one or more anomalies in the sequence of events.
6. The cyber threat defense system according to claim 1 , wherein the predictor is configured to generate likelihoods for anomaly detection and then present the likelihood for the anomaly detection on the user interface.
7. The cyber threat defense system according to claim 1 , wherein the additional contextual information comprises (i) information about the anomaly, (ii) a prediction of what would have been expected and/or (iii) likelihoods for anomaly detection.
8. The cyber threat defense system according to claim 1 , wherein the predictor is configured to provide a notification comprising an anomaly score in addition to the additional contextual information about the one or more anomalies.
9. The cyber threat defense system according to claim 1 , wherein the sequence of events is string data.
10. The cyber threat defense system according to claim 1 , wherein the sequence of events is string data derived from an SaaS event.
11. A method of detecting a cyber threat, the method comprising:
using a modeler to model network data as a sequence of events;
using a predictor to predict a next item in the sequence of events and to identify one or more anomalies in the sequence of events;
using a user interface conveying a notification of the one or more anomalies occurring in a network protected by a cyber threat defense system;
using the predictor to match a JA3 hash of the network data and a domain to particular user agents; and to provide in a notification information about the particular user agents; and
generating at least the notification in response to the predictor identifying the one or more anomalies, the notification conveying on the user interface (i) information about the one or more anomalies, and ii) additional contextual information, beyond a possible score, about the one or more anomalies in order to enhance a user's understanding regarding the identified one or more anomalies.
12. The method according to claim 11 , wherein the predictor is a Transformer deep learning model.
13. The method according to claim 11 , wherein the additional contextual information identifies each anomalous part of an event in the sequence of events.
14. The method according to claim 11 , wherein the additional contextual information identifies a plurality of anomalies in parts of an event in a sequence of events, when multiple anomalies were detected with the identified one or more anomalies in the sequence of events.
15. The method according to claim 11 , further comprising the predictor generating likelihoods for anomaly detection and then present the likelihood for the anomaly detection on the user interface.
16. The method according to claim 11 , wherein the additional contextual information comprises (i) information about the anomaly, (ii) a prediction of what would have been expected and/or (iii) likelihoods for anomaly detection.
17. The method according to claim 11 , wherein the sequence of events is string data derived from a SaaS event.
18. A non-transitory computer-readable medium including executable instructions that, when executed with one or more processors, cause a cyber-threat defense system to perform the method of claim 11 .