# US 2022/0278997 A1 · Multistage analysis of emails to identify security threats

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

- Number: US 2022/0278997 A1
- Document ID: US20220278997A1
- Status: Published application
- Kind: A1
- Application number: 17/677,822
- Filed: 2022-02-22
- Published: 2022-09-01
- Earliest claimed: 2018-12-19
- Assignees: Abnormal Security Corporation
- Applicants: Abnormal Security Corporation
- Inventors: Sanjay Jeyakumar; Jeshua Alexis Bratman; Dmitry Chechik; Abhijit Bagri; Evan Reiser; Sanny Xiao Lang Liao; Yu Zhou Lee; Carlos Daniel Gasperi; Kevin Lau; Kai Jiang; Su Li Debbie Tan; Jeremy Kao; Cheng-Lin Yeh
- Web page: https://patentgrep.com/patent/US20220278997A1

## CPC

- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06F 16/951: Indexing; Web crawling techniques
- G06F 16/9558: {Details of hyperlinks; Management of linked annotations}
- G06F 16/986: {Document structures and storage, e.g. HTML extensions}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G06Q 10/107: Computer-aided management of electronic mailing [e-mailing]
- H04L 51/212: using filtering or selective blocking
- H04L 63/1433: {Vulnerability analysis}
- H04L 63/1483: {service impersonation, e.g. phishing, pharming or web spoofing (detection of rogue wireless access points H04W12/12)}
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Conventional email filtering services are not suitable for recognizing sophisticated malicious emails, and therefore may allow sophisticated malicious emails to reach inboxes by mistake. Introduced here are threat detection platforms designed to take an integrative approach to detecting security threats. For example, after receiving input indicative of an approval from an individual to access past email received by employees of an enterprise, a threat detection platform can download past emails to build a machine learning (ML) model that understands the norms of communication with internal contacts (e.g., other employees) and/or external contacts (e.g., vendors). By applying the ML model to incoming email, the threat detection platform can identify security threats in real time in a targeted manner.

## Claims

### Claim 1

A system, comprising:
a processor configured to:
receive input indicative of an approval to access emails delivered to an employee of an enterprise;
acquire an incoming email addressed to the employee;
extract a primary attribute from the incoming email by parsing content of the incoming email and/or metadata associated with the incoming email;
derive a secondary attribute based on the primary attribute; and
determine whether the incoming email deviates from past email activity by comparing the primary and secondary attributes to a communication profile associated with the employee; and
a memory coupled to the processor and configured to provide the processor with instructions.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processor is further configured to establish, via an application programming interface, a connection with an email system employed by the enterprise.

### Claim 3 (depends on 1)

The system of claim 1, wherein the communication profile includes primary and secondary attributes of past emails delivered to the employee determined to be representative of safe communications.

### Claim 4 (depends on 3)

The system of claim 3, wherein said determining includes discovering whether the primary attribute, the secondary attribute, or the combination of the primary and secondary attributes is included in the communication profile.

### Claim 5 (depends on 1)

The system of claim 1, wherein the primary attribute is sender display name, sender username, Sender Policy Framework (SPF) status, DomainKeys Identified Mail (DKIM) status, number of attachments, number of links in a body of the incoming email, country of origin, information in a header of the incoming email, or an identifier embedded in metadata associated with the incoming email.

### Claim 6 (depends on 1)

The system of claim 1, wherein the processor is further configured to:
establish that the incoming email does not represent a security risk; and
update the communication profile by creating an entry that programmatically associates the first and second attributes.

### Claim 7

A system, comprising:
a processor configured to:
acquire an incoming email addressed to an employee of an enterprise;
extract features for the incoming email in the form of primary and secondary attributes;
employ a machine learning (ML) model that consumes the extracted features to determine whether any indicators of compromise that are representative of security threats exist;
generate a signature for each indicator of compromise; and
cause each signature to be ingested by a database to be used in discovering future attacks with the same features; and
a memory coupled to the processor and configured to provide the processor with instructions.

### Claim 8 (depends on 7)

The system of claim 7, wherein each indicator of compromise is at least one of an Internet Protocol (IP) address, email address, Uniform Resource Locator (URL), or domain.

### Claim 9 (depends on 7)

The system of claim 7, wherein the processor is further configured to perform deep feature extraction to lessen a likelihood of harm from sophisticated security threats.

### Claim 10 (depends on 9)

The system of claim 9, wherein said performing comprises applying a deep learning model to understand content, sentiment, and/or tone of the incoming email.

### Claim 11 (depends on 9)

The system of claim 9, wherein said performing comprises:
accessing a landing page by interacting with a link embedded in the incoming email; and
employing a computer vision algorithm to compare the landing page to a set of known sign-on pages verified as authentic.

### Claim 12 (depends on 9)

The system of claim 9, wherein said performing comprises employing a crawling algorithm to extract information regarding a secondary link that is embedded in an attachment to the incoming email or accessible via a website linked to by a primary link in the incoming email.

### Claim 13

A system, comprising:
a processor configured to:
acquire a series of emails addressed to employees of an enterprise;
identify entitles involved in the series of emails by examining each email;
create a series of signatures for the series of emails, wherein each signature in the series of signatures is associated with a separate email in the series of emails, and wherein each signature identifies one or more entities determined to be involved in the corresponding email;
acquire corpus statistics for the entities determined to be involved in the series of emails;
index the corpus statistics by date; and
store the series of signatures and the indexed corpus statistics in a date-partitioned data structure; and
a memory coupled to the processor and configured to provide the processor with instructions.

### Claim 14 (depends on 13)

The system of claim 13, wherein the processor is further configured to:
acquire an incoming email addressed to an employee of the enterprise;
identify at least one entity involved in the incoming email by examining the incoming email; and
compare the at least one entity against the date-partitioned data structure to establish whether the at least one entity matches any of the series of signatures.

### Claim 15 (depends on 14)

The system of claim 14, wherein the processor is further configured to:
determine that the at least one entity matches a signature in the series of signatures; and
estimate risk posed by the incoming email based on the signature.

### Claim 16 (depends on 15)

The system of claim 15, wherein said estimating comprises:
determining what risk, if any, was posed by the past email corresponding to the signature; and
calculating a risk metric for the incoming email based on the determined risk of the past email.

### Claim 17 (depends on 14)

The system of claim 14, wherein the processor is further configured to:
determine a degree of similarity between the at least one entity and the series of signatures by employing a machine learning (ML) algorithm that probabilistically compares the at least one entity to each signature in the series of signatures; and
estimate risk posed by the incoming email based on an output produced by the ML algorithm.
