Optimizing network traffic obfuscation based on aggregated network performance
In some examples, a method includes receiving, from a plurality of agents executing on scatter network devices, network performance metrics, at least some of the scatter network devices serving as endpoints for logical communication channels formed via a communication channel provider for which a first Internet service provider provides Internet backhaul and the logical communication channels traverse a first relay; aggregating the network performance metrics received from the plurality of agents; analyzing the aggregated network performance metrics to determine operational characteristics of a network; determining, based on the operational characteristics of the network, that the Internet service provider has transitioned from the first Internet service provider to a second Internet service provider to provide the Internet backhaul; and responsive to the determining, providing an instruction to the plurality of agents to modify operational settings of the agents to form logical communication channels that traverse a second relay.
1 . A method of optimizing network traffic obfuscation based on aggregated network performance, comprising:
receiving, from a plurality of agents executing on scatter network devices, network performance metrics, at least some of the scatter network devices serving as endpoints for logical communication channels formed via a communication channel provider for which a first Internet service provider provides Internet backhaul and the logical communication channels traverse a first relay;
aggregating the network performance metrics received from the plurality of agents;
analyzing the aggregated network performance metrics to determine operational characteristics of a network;
determining, based on the operational characteristics of the network, that the Internet service provider has transitioned from the first Internet service provider to a second Internet service provider to provide the Internet backhaul; and
responsive to the determining, providing an instruction to the plurality of agents to modify operational settings of the agents to form logical communication channels that traverse a second relay.
2 . The method of claim 1 , further comprising analyzing the aggregated network performance metrics according to statistical analysis.
3 . The method of claim 1 , further comprising analyzing the aggregated network performance metrics according to machine learning processing.
4 . The method of claim 1 , wherein the first relay is optimized for the first Internet service provider, and wherein the second relay is optimized for the second Internet service provider.
5 . The method of claim 1 , further comprising determining that the Internet service provider has transitioned from the first Internet service provider to the second Internet service provider to provide the Internet backhaul responsive to determining that a plurality of scatter network devices each having logical communication channels that traverse the first relay are experiencing network performance issues.
6 . The method of claim 1 , wherein the instruction is a profile according to which the agents form the logical communication channels.
7 . A method of optimizing network traffic obfuscation based on aggregated network performance, comprising:
obfuscating, by a scatter network node comprising at least one non-transitory memory and at least one processor, a first plurality of data packets according to a first machine learning (“ML”) obfuscation model of a plurality of ML obfuscation models associated with a logical communication channel;
transmitting, by the scatter network node, the obfuscated first plurality of data packets via the logical communication channel to a counterpart scatter network node;
transmitting, by an agent stored in the at least one non-transitory memory and executable by the at least one processor, performance metrics associated with the logical communication channel to a server;
receiving, by the agent from the server, a control input configured to cause the scatter network node to select, by the agent, a second ML obfuscation model of the plurality of ML obfuscation models;
obfuscating, by the scatter network node, a second plurality of data packets according to the second ML obfuscation model; and
transmitting, by the scatter network node, the obfuscated second plurality of data packets via the logical communication channel to the counterpart scatter network node.
8 . The method of claim 7 , wherein the performance metrics associated with the logical communication channel indicate that performance of the logical communication channel is less than a threshold.
9 . The method of claim 8 , wherein, responsive to the performance of the logical communication channel being less than the threshold, the method further comprises:
processing, by the server and via a machine learning process, the performance metrics to determine a cause of the performance of the logical communication channel being less than the threshold;
determining by the server, an operational modification for the agent to increase the performance of the logical communication channel; and
providing the operational modification to the agent.
10 . The method of claim 9 , wherein the operational modification is a change from the first ML obfuscation model to the second ML obfuscation model.
11 . The method of claim 9 , wherein the operational modification is a change to a profile according to which the agent forms the logical communication channel.
12 . The method of claim 9 , wherein the operational modification is a change from the logical communication channel to a second logical communication channel.
13 . The method of claim 9 , wherein the operational modification is a change to a weighting of a parameter of a rewards function according to which operation of the scatter network element is scored.
14 . The method of claim 9 , wherein the operational modification is a change to routing of the logical communication channel.
15 . A server, comprising:
at least one non-transitory memory;
at least one processor;
a network traffic obfuscation application stored in the at least one non-transitory memory that, when executed by the at least one processor:
receives, from a plurality of agents executing on scatter network devices, network performance metrics for a plurality of logical communication channels established among a plurality of communication mediums;
aggregates the network performance metrics received from the plurality of agents;
analyzes the aggregated network performance metrics via machine learning processing to determine operational characteristics of a network;
determines that at least one of the operational characteristics is less than a threshold;
responsive to determining that the at least one of the operational characteristics is less than the threshold, determines a modification to operation of at least one of the plurality of agents to increase the operational characteristics; and
transmits the modification to the scatter network devices.
16 . The server of claim 15 , wherein the network performance metrics include bandwidth, latency, throughput, and obfuscation characteristics.
17 . The server of claim 15 , wherein the modification is a change to a weighting of a parameter of a rewards function according to which operation of the scatter network devices are scored.
18 . The server of claim 15 , wherein the modification is a change to a profile according to which at least some of the plurality of agents form logical communication channels.
19 . The server of claim 15 , wherein the modification is a change from routing via a first network relay to routing via a second network relay.
20 . The server of claim 15 , wherein executing the application further causes the at least one processor to perform border gateway protocol surveillance of a network in which at least some of the scatter network devices operate.