Determining entity maliciousness based on associated entities
The behavior analysis engine can identify malicious entities based on connections between the entity and other entities. The behavior analysis engine receives an entity from the network traffic hub and identifies entities that are connected to the entity within a threshold degree of separation. The behavior analysis engine applies a recursive process to the entity whereby the behavior analysis engine determines whether an entity is malicious based on whether its connections within a threshold degree of separation are malicious. The behavior analysis engine uses the maliciousness of the entities' connections to determine whether the entity is malicious and, if the entity is malicious, the behavior analysis engine may instruct the network traffic hub to block network communications associated with the malicious entity.
1. A method comprising:
generating, at a behavior analysis engine, an entity analysis model by determining connections between a set of known malicious entities and a set of known non-malicious entities, wherein a connection between entities represents that the entities are associated with one another;
receiving, at the behavior analysis engine, an entity from a network traffic hub in a local network, the entity comprising one of a domain and a network address that is associated with a network communication that is sent from a source device outside of the local network to a networked device in the local network;
identifying, by using the entity analysis model, a set of connected entities associated with the received entity;
determining relationship information for the received entity by applying a recursive process to each entity of the set of connected entities to determine a maliciousness of each entity of the set of connected entities;
determining whether the received entity is malicious based on the determined relationship information; and
transmitting, by the behavior analysis engine, processing instructions to the network traffic hub based on the determination of whether the received entity is malicious.
2. The method of claim 1 , wherein the set of connected entities are identified based on Whois lookups, reverse Domain Name Server (DNS) lookups, or via OpenSSL handshakes with domains.
3. The method of claim 1 , wherein the relationship information describes the set of connected entities and characteristics of connections between the set of connected entities.
4. The method of claim 1 , wherein the relationship information identifies which entities of the set of connected entities are malicious.
5. The method of claim 1 , wherein the entity analysis model is trained by determining relationship information for each entity of the set of connected entities.
6. The method of claim 1 , further comprising, responsive to determining that the received entity is malicious, transmitting the processing instructions to the network traffic hub to block network traffic associated with the received entity.
7. The method of claim 1 , further comprising, responsive to determining that the received entity is not malicious, transmitting the processing instructions to the network traffic hub to allow the received entity to communicate with networked devices in the local network.
8. A non-transitory computer-readable medium comprising instructions that, when executed by a processor, cause the processor to:
generate, at a behavior analysis engine, an entity analysis model by determining connections between a set of known malicious entities and a set of known non-malicious entities, wherein a connection between entities represents that the entities are associated with one another;
receive, at the behavior analysis engine, an entity from a network traffic hub in a local network, the entity comprising one of a domain and a network address that is associated with a network communication that is sent from a source device outside of the local network to a networked device in the local network;
identify, by using the entity analysis model, a set of connected entities associated with the received entity;
determine relationship information for the received entity by applying a recursive process to each entity of the set of connected entities to determine a maliciousness of each entity of the set of connected entities;
determine whether the received entity is malicious based on the determined relationship information; and
transmit processing instructions to the network traffic hub based on the determination of whether the received entity is malicious.
9. The computer-readable medium of claim 8 , further comprising instructions that cause the processor to, responsive to determining that the received entity is malicious, transmit the processing instructions to the network traffic hub to block network traffic associated with the received entity.
10. The computer-readable medium of claim 8 , further comprising instructions that cause the processor to, responsive to determining that the received entity is not malicious, transmit the processing instructions to the network traffic hub to allow the received entity to communicate with networked devices in the local network.
11. A computing device comprising:
a memory; and
a processor device coupled to the memory and configured to:
generate, at a behavior analysis engine, an entity analysis model by determining connections between a set of known malicious entities and a set of known non-malicious entities, wherein a connection between entities represents that the entities are associated with one another;
receive, at the behavior analysis engine, an entity from a network traffic hub in a local network, the entity comprising one of a domain and a network address that is associated with a network communication that is sent from a source device outside of the local network to a networked device in the local network;
identify, by using the entity analysis model, a set of connected entities associated with the received entity;
determine relationship information for the received entity by applying a recursive process to each entity of the set of connected entities to determine a maliciousness of each entity of the set of connected entities;
determine whether the received entity is malicious based on the determined relationship information; and
transmit processing instructions to the network traffic hub based on the determination of whether the received entity is malicious.