System for reducing false alerts from network detection and response tool

1 . A system, comprising:

processor configured to:

retrieve traffic data associated with a network session between a client device and a server, wherein the traffic data comprises at least one of: a first set of parameters associated with the client device, and a second set of parameters associated with the server;

determine a client entropy value based on the first set of parameters associated with the client device based on the retrieved traffic data;

determine a server entropy value based on the second set of parameters associated with the server based on the retrieved traffic data;

determine a non-empty packet value based on the first set of parameters associated with the client device and the second set of parameters associated with the server;

provide the client entropy value, the server entropy value, and the non-empty packet value, as an input, to a machine learning (ML) model; and

generate an alert based on an output of the ML model.

2 . The system of claim 1 , wherein the first set of parameters comprises at least one of: transmitted bytes data, client device payload data, client device address packet data, and client device non-empty packet count data.

3 . The system of claim 2 , wherein the client entropy value is determined based on the transmitted bytes data, and wherein the client entropy value corresponds to a number of bytes transmitted from the client device to the server in the network session.

4 . The system of claim 1 , wherein the second set of parameters comprises at least one of: received bytes data, server payload data, server address packet data, and server non-empty packet count data.

5 . The system of claim 4 , wherein the server entropy value is further determined based on the received bytes data, and wherein the server entropy value corresponds to a number of bytes received by the server from the client device in the network session.

6 . The system of claim 1 , wherein the non-empty packet value is further determined based on client device non-empty packet count data and server non-empty packet count data.

7 . The system of claim 1 , wherein the processor is further configured to:

determine, at a first timestamp, an occurrence of a malicious activity in a first network session;

detect, at the first timestamp, a trigger based on the determination of the occurrence of the malicious activity; and

provide the client entropy value, the server entropy value, and the non-empty packet value, as the input, to the ML model based on the detection of the trigger.

8 . The system of claim 7 , wherein the processor is further configured to determine the occurrence of the malicious activity in the first network session using a set of malicious activity detection rules.

9 . The system of claim 1 , wherein the processor is further configured to:

classify the network session as one of: a normal network session or a malicious network session based on the output of the ML model;

generate the alert based on the classification of the network session; and

render the generated alert.

10 . The system of claim 1 , wherein the ML model is pre-trained to classify the network session as one of: a normal network session and a malicious network session based on the retrieved traffic data.

11 . The system of claim 1 , wherein the processor is further configured to train the ML model based on the retrieved traffic data, and the generated alert.

12 . A method, comprising:

retrieving traffic data associated with a network session between a client device and a server, wherein the traffic data comprises at least one of: a first set of parameters associated with the client device, and a second set of parameters associated with the server;

determining a client entropy value based on the first set of parameters associated with the client device based on the retrieved traffic data;

determining a server entropy value based on the second set of parameters associated with the server based on the retrieved traffic data;

determining a non-empty packet value based on the first set of parameters associated with the client device and the second set of parameters associated with the server;

providing the client entropy value, the server entropy value, and the non-empty packet value, as an input, to a machine learning (ML) model; and

generating an alert based on an output of the ML model.

13 . The method of claim 12 , wherein the first set of parameters comprises at least one of: transmitted bytes data, client device payload data, client device address packet data, and client device non-empty packet count data.

14 . The method of claim 12 , wherein the non-empty packet value is further determined based on client device non-empty packet count data and server non-empty packet count data.

15 . The method of claim 12 , further comprising:

determining, at a first timestamp, an occurrence of a malicious activity in a first network session;

detecting, at the first timestamp, a trigger based on the determination of the occurrence of the malicious activity; and

providing the client entropy value, the server entropy value, and the non-empty packet value, as the input, to the ML model based on the detection of the trigger.

16 . The method of claim 15 , further comprising determining the occurrence of the malicious activity in the first network session using a set of malicious activity detection rules.

17 . The method of claim 12 , further comprising:

classifying the network session as one of: a normal network session or a malicious network session based on the output of the ML model;

generating the alert based on the classification of the network session; and

rendering the generated alert.

18 . The method of claim 12 , wherein the ML model is pre-trained to classify the network session as one of: a normal network session and a malicious network session based on the retrieved traffic data.

19 . The method of claim 12 , further comprising training the ML model based on the retrieved traffic data, and the generated alert.

20 . A non-transitory computer-readable medium having stored thereon, computer-executable instructions that when executed by a processor of a system, causes the processor to execute operations, the operations comprising:

retrieving traffic data associated with a network session between a client device and a server, wherein the traffic data comprises at least one of: a first set of parameters associated with the client device, and a second set of parameters associated with the server;

determining a client entropy value based on the first set of parameters associated with the client device based on the retrieved traffic data;

determining a server entropy value based on the second set of parameters associated with the server based on the retrieved traffic data;

determining a non-empty packet value based on the first set of parameters associated with the client device and the second set of parameters associated with the server,

providing the client entropy value, the server entropy value, and the non-empty packet value, as an input, to a machine learning (ML) model; and

generating an alert based on an output of the ML model.