Detection of malicious activity within a network
Techniques and systems for detecting malicious activity within a network are provided herein. A method for detecting malicious activity within a network may include receiving, by a network-based authentication system, a network transaction. The network-based authentication system may identify a first attribute of the network transaction. The method may also include selecting, by the network-based authentication system, a first learning statistical model and a second learning statistical model from a plurality of models for handling the network transaction. Each of the first learning statistical model and the second learning statistical model may create a likelihood that the network transaction is authentic. The first learning statistical model may calculate a first score and the second learning statistical score may calculate a second score. Based on a comparison of the first score to a first threshold and the second score to a second threshold, the network transaction may be authenticated.
1 . A system comprising:
one or more processing devices; and
memory communicatively coupled with and readable by the one or more processing devices and having stored therein processor-readable instructions which, when executed by the one or more processing devices, cause the one or more processing devices to perform operations comprising:
receiving a network transaction;
identifying a first attribute of the network transaction;
selecting a learning statistical model from a plurality of models for use with respect to the network transaction, wherein the learning statistical model is selected based at least in part on the first attribute of the network transaction;
calculating, using the learning statistical model, a score, wherein the learning statistical model indicates a likelihood that the network transaction is authentic; and
comparing the first-score to a threshold;
wherein the system performs real-time analysis to facilitate accuracy and authorization speed for one or more network transactions and, based at least in part on the comparing the score to the threshold, generates a visual representation of one or more nodes related to the network transaction to facilitate triggering automated remedial action for one or more potentially malicious transactions.
2 . The system as recited in claim 1 , wherein the visual representation shows connections between different derivative entities that are recognized using network analytics.
3 . The system as recited in claim 2 , wherein the visual representation is generated based at least in part on scoring each network transaction of a plurality of network transactions to indicate a likelihood that each network transaction is authentic.
4 . The system as recited in claim 3 , wherein the generating is based at least in part on filtering out at least one node associated with one or more scores that fail to satisfy the threshold, and the visual representation does not show the at least one node.
5 . The system as recited in claim 1 , wherein the one or more nodes are limited based at least in part on network transactions having been associated with a geographical region.
6 . The system as recited in claim 1 , wherein the one or more nodes are limited based at least in part on network transactions having been performed within a temporal limit.
7 . The system as recited in claim 1 , wherein the visual representation shows one or more entities within a number of relationships to the one or more nodes.
8 . A method comprising:
receiving a network transaction;
performing real-time analysis to facilitate accuracy and authorization speed for one or more network transactions based at least in part on:
identifying a first attribute of the network transaction;
selecting a learning statistical model from a plurality of models for use with respect to the network transaction, wherein the learning statistical model is selected based at least in part on the first attribute of the network transaction;
calculating, using the learning statistical model, a score, wherein the learning statistical model indicates a likelihood that the network transaction is authentic; and
comparing the first-score to a threshold; and
based at least in part on the comparing the score to the threshold, generating a visual representation of one or more nodes related to the network transaction to facilitate triggering automated remedial action for one or more potentially malicious transactions.
9 . The method as recited in claim 8 , wherein the visual representation shows connections between different derivative entities that are recognized using network analytics.
10 . The method as recited in claim 9 , wherein the visual representation is generated based at least in part on scoring each network transaction of a plurality of network transactions to indicate a likelihood that each network transaction is authentic.
11 . The method as recited in claim 10 , wherein the generating is based at least in part on filtering out at least one node associated with one or more scores that fail to satisfy the threshold, and the visual representation does not show the at least one node.
12 . The method as recited in claim 8 , wherein the one or more nodes are limited based at least in part on network transactions having been associated with a geographical region.
13 . The method as recited in claim 8 , wherein the one or more nodes are limited based at least in part on network transactions having been performed within a temporal limit.
14 . The method as recited in claim 8 , wherein the visual representation shows one or more entities within a number of relationships to the one or more nodes.
15 . One or more non-transitory, machine-readable media having machine-readable instructions thereon which, when executed by one or more processing devices, cause a system to perform operations comprising:
receiving a network transaction;
performing real-time analysis to facilitate accuracy and authorization speed for one or more network transactions based at least in part on:
identifying a first attribute of the network transaction;
selecting a learning statistical model from a plurality of models for use with respect to the network transaction, wherein the learning statistical model is selected based at least in part on the first attribute of the network transaction;
calculating, using the learning statistical model, a score, wherein the learning statistical model indicates a likelihood that the network transaction is authentic; and
comparing the first-score to a threshold; and
based at least in part on the comparing the score to the threshold, generating a visual representation of one or more nodes related to the network transaction to facilitate triggering automated remedial action for one or more potentially malicious transactions.
16 . The one or more non-transitory, machine-readable media as recited in claim 15 , wherein the visual representation shows connections between different derivative entities that are recognized using network analytics.
17 . The one or more non-transitory, machine-readable media as recited in claim 16 , wherein the visual representation is generated based at least in part on scoring each network transaction of a plurality of network transactions to indicate a likelihood that each network transaction is authentic.
18 . The one or more non-transitory, machine-readable media as recited in claim 17 , wherein the generating is based at least in part on filtering out at least one node associated with one or more scores that fail to satisfy the threshold, and the visual representation does not show the at least one node.
19 . The one or more non-transitory, machine-readable media as recited in claim 15 , wherein the one or more nodes are limited based at least in part on network transactions having been associated with a geographical region.
20 . The one or more non-transitory, machine-readable media as recited in claim 15 , wherein the one or more nodes are limited based at least in part on network transactions having been performed within a temporal limit.