# US 2019/0379700 A1 · Systems and methods for alert prioritization using security events graph

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0379700 A1
- Document ID: US20190379700A1
- Status: Published application
- Kind: A1
- Application number: 16/361,023
- Filed: 2019-03-21
- Published: 2019-12-12
- Earliest claimed: 2018-06-12
- Assignees: Netskope, Inc.
- Applicants: Netskope, Inc.
- Inventors: Raymond Joseph Canzanese, JR.; Joshua David Batson
- Web page: https://patentgrep.com/patent/US20190379700A1

## CPC

- H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)}
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06F 16/906: Clustering; Classification
- H04L 41/069: using logs of notifications; Post-processing of notifications
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The technology disclosed includes a system to group security alerts generated in a computer network and prioritize grouped security alerts for analysis. The system includes graphing entities in the computer network as entities connected by one or more edges. Native scores for pending alerts are assigned to nodes or to edges between the nodes. A connection type is assigned to each edge and weights are assigned to edges representing relationship strength between the nodes. The technology disclosed includes traversing the graph starting at starting nodes and propagating native scores through and to neighboring nodes connected by the edges. Aggregate score for a visited node is calculated by accumulating propagated scores at visited nodes with their respective native scores. The technology disclosed forms clusters of connected nodes in the graph that have a respective aggregate score above a selected threshold. The clusters are ranking and prioritized for analysis.

## Claims

### Claim 1

A method of grouping security alerts generated from a computer network and prioritizing grouped security alerts for analysis, including:
graphing entities in the computer network as nodes connected by one or more edges;
assigning a connection type to each edge, wherein the connection type represents a relationship type between the nodes connected by the edge, and assigning a weight to each edge representing a relationship strength between the nodes connected;
assigning native scores from the security alerts to the nodes or to edges between the nodes;
traversing the graph, starting at starting nodes with non-zero native scores, visiting the nodes in the graph and propagating the native scores from the starting nodes attenuated by the weight assigned to an edge traversed, the traversing extending for at least a predetermined span from the starting nodes, through and to neighboring nodes connected by the edges;
normalizing and accumulating propagated scores at visited nodes, summed with the native score assigned to the visited nodes to generate aggregate scores for the visited nodes, wherein normalizing the propagated scores at the visited nodes includes attenuating a propagated score based on a number of contributing neighboring nodes of a respective visited node to form a normalized score;
forming clusters of connected nodes in the graph that have a respective aggregate score above a selected threshold, which clusters are separated from other clusters through nodes that have a respective aggregate score below the selected threshold; and
ranking and prioritizing for analysis, the clusters according to the aggregate scores of the nodes in the formed clusters.

### Claim 2 (depends on 1)

The method of claim 1, wherein the graphing entities in the computer network as nodes further includes connecting the nodes by one or more directed edges.

### Claim 3 (depends on 1)

The method of claim 1, wherein the graphing entities in the computer network as nodes further includes connecting the nodes by directed and bi-directed edges.

### Claim 4 (depends on 1)

The method of claim 1, further including assigning native scores for pending alerts to edges between the nodes.

### Claim 5 (depends on 4)

The method of claim 4, further including distributing the assigned native scores from the edges to nodes connected to the edges.

### Claim 6 (depends on 5)

The method of claim 5, wherein the edges include a loop edge connected to a single node, the method further including, assigning the native score of the loop edge to the single node.

### Claim 7 (depends on 1)

The method of claim 1, wherein the connection type assigned to each edge includes at least one of an association connection type, a communication connection type, a failure connection type, a location connection type, and an action or an operation connection type.

### Claim 8 (depends on 1)

The method of claim 1, wherein the predetermined span is up to five edge or node hops from the starting node.

### Claim 9 (depends on 1)

The method of claim 1, wherein propagating native scores from the starting nodes, through and to neighboring nodes connected by the edges is limited to when the propagated score is above a selected threshold and stops when the propagated score is below the selected threshold.

### Claim 10 (depends on 1)

The method of claim 1, wherein normalizing the propagated score at the visited node, further includes attenuating the propagated score at the visited node in proportion to the number of neighboring nodes connected to the visited node by edges of the same connection type.

### Claim 11 (depends on 1)

The method of claim 1, further including, attenuating the propagated scores at the visited nodes by dividing the propagated scores by a sum of weights of relationship strengths on edges connected to the visited node.

### Claim 12 (depends on 1)

The method of claim 1, wherein the clusters of connected nodes are separated by at least one node that has an aggregate score below a selected threshold.

### Claim 13 (depends on 1)

The method of claim 1, wherein the clusters of connected nodes are separated by at least one node in a pair of connected nodes that has an aggregate score less than ten times the aggregate score of the other node in the pair of connected nodes.

### Claim 14

A system including one or more processors coupled to memory, the memory loaded with computer instructions to group security alerts generated from a computer network and prioritize grouped security alerts for analysis, the instructions, when executed on the processors, implement actions comprising:
graphing entities in the computer network as nodes connected by one or more edges;
assigning a connection type to each edge, wherein the connection type represents a relationship type between the nodes connected by the edge, and assigning a weight to each edge representing a relationship strength between the nodes connected;
assigning native scores from the security alerts to the nodes or to edges between the nodes;
traversing the graph, starting at starting nodes with non-zero native scores, visiting the nodes in the graph and propagating the native scores from the starting nodes attenuated by the weight assigned to an edge traversed, the traversing extending for at least a predetermined span from the starting nodes, through and to neighboring nodes connected by the edges;
normalizing and accumulating propagated scores at visited nodes, summed with the native score assigned to the visited nodes to generate aggregate scores for the visited nodes, wherein normalizing the propagated scores at the visited nodes includes attenuating a propagated score based on a number of contributing neighboring nodes of a respective visited node to form a normalized score;
forming clusters of connected nodes in the graph that have a respective aggregate score above a selected threshold, which clusters are separated from other clusters through nodes that have a respective aggregate score below the selected threshold; and
ranking and prioritizing for analysis, the clusters according to the aggregate scores of the nodes in the formed clusters.

### Claim 15 (depends on 14)

The system of claim 14, wherein the graphing entities in the computer network as nodes further includes connecting the nodes by one or more directed edges.

### Claim 16 (depends on 14)

The system of claim 14, wherein the graphing entities in the computer network as nodes further includes connecting the nodes by directed and bi-directed edges.

### Claim 17 (depends on 14)

The system of claim 14, further implementing actions comprising:
assigning native scores for pending alerts to edges between the nodes.

### Claim 18

A non-transitory computer readable storage medium impressed with computer program instructions to group security alerts generated from a computer network and prioritize grouped security alerts for analysis, the instructions, when executed on a processor, implement a method comprising:
graphing entities in the computer network as nodes connected by one or more edges;
assigning a connection type to each edge, wherein the connection type represents a relationship type between the nodes connected by the edge, and assigning a weight to each edge representing a relationship strength between the nodes connected;
assigning native scores from the security alerts to the nodes or to edges between the nodes;
traversing the graph, starting at starting nodes with non-zero native scores, visiting the nodes in the graph and propagating the native scores from the starting nodes attenuated by the weight assigned to an edge traversed, the traversing extending for at least a predetermined span from the starting nodes, through and to neighboring nodes connected by the edges;
normalizing and accumulating propagated scores at visited nodes, summed with the native score assigned to the visited nodes to generate aggregate scores for the visited nodes, wherein normalizing the propagated scores at the visited nodes includes attenuating a propagated score based on a number of contributing neighboring nodes of a respective visited node to form a normalized score;
forming clusters of connected nodes in the graph that have a respective aggregate score above a selected threshold, which clusters are separated from other clusters through nodes that have a respective aggregate score below the selected threshold; and
ranking and prioritizing for analysis, the clusters according to the aggregate scores of the nodes in the formed clusters.

### Claim 19 (depends on 18)

The non-transitory computer readable storage medium of claim 18, wherein the connection type assigned to each edge includes at least one of an association connection type, a communication connection type, a failure connection type, a location connection type, and an action or an operation connection type.

### Claim 20 (depends on 18)

The non-transitory computer readable storage medium of claim 18, wherein propagating native scores from the starting nodes, through and to neighboring nodes connected by the edges is limited to when the propagated score is above a selected threshold and stops when the propagated score is below the selected threshold.
