# US 2021/0067531 A1 · Context informed abnormal endpoint behavior detection

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

- Number: US 2021/0067531 A1
- Document ID: US20210067531A1
- Status: Published application
- Kind: A1
- Application number: 16/557,549
- Filed: 2019-08-30
- Published: 2021-03-04
- Earliest claimed: 2019-08-30
- Assignees: Palo Alto Networks, Inc.
- Applicants: Palo Alto Networks, Inc.
- Inventors: Shai Meir; Dany Cohen; Arkady Miasnikov; Ohad Ohayon
- Web page: https://patentgrep.com/patent/US20210067531A1

## CPC

- G06F 21/554: {involving event detection and direct action}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- G06F 21/552: {involving long-term monitoring or reporting}
- G06N 20/00: Machine learning
- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Adaptive normal profiles are generated at a hierarchical scope corresponding to a set of endpoints and a process. Abnormal endpoint activity is detected by verifying whether event data tracking activity on the set of endpoints conforms to the adaptive normal profiles. False positives are reduced by verifying alarms correspond to normal endpoint activity. Abnormal event data is forwarded to a causality chain identifier that identifies abnormal chains of processes for the abnormal endpoint activity. A trained threat detection model receives abnormal causality chains from the causality chain identifier and indicates a likelihood of corresponding to a malicious attack that indicates abnormal endpoint behavior.

## Claims

### Claim 1

A method comprising:
determining, from event information, a first process identifier of a first process and an endpoint identifier of a first endpoint;
identifying a set of one or more process profiles from a plurality of process profiles based, at least in part, on the process identifier and the endpoint identifier, wherein the set of process profiles indicates process activity of the first process determined to be statistically normal with respect to process activity of the first process on a plurality of endpoints within at least one scope that includes the first endpoint;
evaluating the event information against the set of process profiles to determine whether the event information conforms to at least a first of the set of process profiles; and
based on a determination that the event information does not conform to at least a first of the set of process profiles, indicating that the event information corresponds to an abnormality for the first process.

### Claim 2 (depends on 1)

The method of claim 1 further comprising detecting the event information from monitoring the first process on the first endpoint.

### Claim 3 (depends on 1)

The method of claim 1 further comprising determining the event information from an alarm.

### Claim 4 (depends on 3)

The method of claim 3 further comprising marking the alarm as a false positive based on a determination that the event information at least conforms to a first of the set of processes.

### Claim 5 (depends on 1)

The method of claim 1, wherein identifying the set of process profiles from the plurality of process profiles comprises identifying at least one process profile having a scope greater than the individual first process.

### Claim 6 (depends on 1)

The method of claim 1, wherein evaluating the event information against the set of process profiles comprises determining whether a first of the set of process profiles includes an entry that indicates a combination of an activity type indicated in the event information and a first path that at least partially matches a second path indicated in the event information.

### Claim 7 (depends on 6)

The method of claim 6 further comprising normalizing the second path indicated in the event information prior to evaluating the event information against the set of process profiles.

### Claim 8 (depends on 7)

The method of claim 7, wherein normalizing the second path indicated in the event information comprises:
identifying, from a set of path elements in the second path, a set of common path elements associated with a first set of standard path elements;
replacing the set of common path elements with the first set of standard path elements;
identifying a type of path associated with the second path;
identifying a set of randomized path elements from the set of path elements;
replacing the set of randomized path elements with a second set of standard path elements; and
synthesizing the first set of standard path elements, the second set of standard path elements, and the type of path.

### Claim 9 (depends on 8)

The method of claim 8, wherein identifying the set of randomized path elements comprises:
for each path element in the second path,
determining a likelihood that the path element is randomized based, at least in part, on a statistical model; and
based on the likelihood being above a threshold likelihood, adding the path element to the set of randomized path elements.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
based on a determination that the event information does not conform to at least a first of the set of process profiles, determining a causality graph corresponding to the first process.

### Claim 11 (depends on 10)

The method of claim 10, wherein determining the causality graph corresponding to the first process comprises determining at least one of a set of processes and a set of events that both directly and indirectly relate to the first process.

### Claim 12 (depends on 10)

The method of claim 10 further comprising inputting the causality graph or data generated from the causality graph into a trained detection model to determine likelihood that the causality graph corresponds to a threat or attack.

### Claim 13

A non-transitory, computer-readable medium having program code stored thereon the program code comprising instructions to:
determine, for a first process, a first plurality of classifiers for process activities of the first process that satisfy a first criterion of normal activity for the first process, wherein the determination of the first plurality of classifiers for process activities that satisfy the first criterion of normal activity is based, at least in part, on first statistics from event data corresponding to the first process across a plurality of endpoints that have hosted the first process;
determine, for the first process, a second plurality of classifiers for process activities of the first process that satisfy a second criterion of normal activity for the first process, wherein the determination of the second plurality of classifiers for process activities that satisfy the second criterion of normal activity is based, at least in part, on second statistics from event data corresponding to the first process on a first of the plurality of endpoints;
generate a first profile with the first plurality of classifiers and associate the first profile with a first hierarchical scope that encompasses the plurality of endpoints; and
generate a second profile with the second plurality of classifiers and associate the second profile with a second hierarchical scope that only encompasses the first endpoint.

### Claim 14 (depends on 13)

The computer-readable medium of claim 13, wherein determining the first plurality of classifiers comprises determining common file paths corresponding to event data for the first process based, at least in part, on the first statistics from event data corresponding to the first process across a plurality of endpoints that have hosted the first process.

### Claim 15 (depends on 14)

The computer-readable medium of claim 14, wherein determining the first plurality of classifiers further comprises determining file types corresponding to common paths for the first process.

### Claim 16

An apparatus comprising:
a processor; and
a machine-readable medium having instructions stored thereon that are executable by the processor to cause the apparatus to,
determine a plurality of processes that do not conform to a plurality process profiles corresponding to the plurality of processes;
identify a serialized plurality of processes from the plurality of processes based, at least in part, on an abnormal causality chain of processes indicated in event information for the plurality of processes;
determine, based on inputting an indication of the serialized plurality of processes into a trained detection model, a likelihood that activity of the serialized plurality of processes is abnormal; and
based on the likelihood being higher than a threshold likelihood, indicate a malicious attack corresponding to the serialized plurality of processes.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein the machine-readable medium further has stored thereon instructions executable by the processor to cause the apparatus to determine the abnormal causality chain of processes indicated in the event information based, at least in part, on the plurality of processes and a causality graph corresponding to the plurality of processes.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the instructions executable by the processor to cause the apparatus to determine the abnormal causality chain of processes indicated in the event information comprise instructions to,
identify a set of one or more causality chains of processes indicated in the event information based, at least in part, on the plurality of processes and a causality graph corresponding to the plurality of processes; and
detect the abnormal causality chain of processes based, at least in part, on statistics from event information corresponding to causality chains for the plurality of processes.

### Claim 19 (depends on 17)

The apparatus of claim 17, wherein the machine-readable medium further has stored thereon instructions executable by the processor to cause the apparatus to generate the causality graph corresponding to the plurality of processes based, at least in part, on a determination that event information for a first process in the plurality of processes and event information for a second process in the plurality of processes are directly or indirectly related.

### Claim 20 (depends on 16)

The apparatus of claim 16, wherein the trained detection model is a machine-learning based model.
