# US 2023/0412622 A1 · Methods, systems, and devices to validate ip addresses

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

- Number: US 2023/0412622 A1
- Document ID: US20230412622A1
- Status: Published application
- Kind: A1
- Application number: 17/842,940
- Filed: 2022-06-17
- Published: 2023-12-21
- Earliest claimed: 2022-06-17
- Assignees: AT&T Intellectual Property I, L.P.
- Applicants: AT&T Intellectual Property I, L.P.
- Inventors: Srivathsan Srinivasagopalan; Ganesh Subramaniam; Robert Archibald
- Web page: https://patentgrep.com/patent/US20230412622A1

## CPC

- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/20: Ensemble learning
- 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

Aspects of the subject disclosure may include, for example, obtaining a first group of Internet Protocol (IP) addresses from a group of network devices, and determining a second group of IP addresses from the first group of IP addresses includes possible malicious IP addresses utilizing a machine learning application. Further embodiments can include obtaining a first group of attributes of malicious IP addresses from a first repository, and determining a third group of IP addresses from the second group of IP addresses includes possible malicious IP addresses based on the first group of attributes. Additional embodiments can include receiving user-generated input indicating a fourth group of IP addresses from the third group of IP addresses includes possible malicious IP addresses, and transmitting a notification to a group of communication devices indicating that the fourth group of IP address includes possible malicious IP addresses. Other embodiments are disclosed.

## Claims

### Claim 1

A device, comprising:
a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
obtaining a first group of Internet Protocol (IP) addresses from a group of network devices;
determining a second group of IP addresses from analyzing network flow traffic among the first group of IP addresses and one or more external IP addresses that includes possible malicious IP addresses utilizing a machine learning application;
obtaining a first group of attributes of malicious IP addresses from a first repository;
determining a third group of IP addresses from the second group of IP addresses includes possible malicious IP addresses based on the first group of attributes;
receiving user-generated input indicating a fourth group of IP addresses from the third group of IP addresses includes possible malicious IP addresses; and
transmitting a notification to a group of communication devices indicating that the fourth group of IP address includes possible malicious IP addresses.

### Claim 2 (depends on 1)

The device of claim 1, wherein the first group of attributes comprise one or more of number of passive domain name system (DNS) servers, number of communicating files, number of uniform resource locators (URLs), number of related network based intrusion detection system (NIDS), number of pulses in the first repository, number of indicator facts, classification within the first repository, number of open ports, number and kind of anti-virus detections, number and kind of intrusion detection system (IDS) detections, certificate information, IDS categories, URLs and dates, and reports from trusted vendors.

### Claim 3 (depends on 1)

The device of claim 1, wherein the determining of the third group of IP addresses comprises generating a group of rules from the first group of attributes.

### Claim 4 (depends on 3)

The device of claim 3, wherein the generating of the group of rules comprises determining a group of attribute thresholds based on the first group of attributes, wherein the group of rules comprises rules based on not satisfying each of the group of attribute thresholds.

### Claim 5 (depends on 4)

The device of claim 4, wherein the group of attribute thresholds comprises a passive DNS server threshold, a communicating files threshold, an URLs threshold, a NIDS threshold, a pulses threshold, an indicator facts threshold, an open ports threshold, an anti-virus detection threshold, and an IDS detection threshold.

### Claim 6 (depends on 3)

The device of claim 3, wherein the determining of the third group of IP addresses comprises:
identifying a first attribute associated with a first IP address from the second group of IP addresses; and
determining that the first IP address is a possible malicious IP address in response to determining that the first attribute does not satisfy a first attribute threshold.

### Claim 7 (depends on 1)

The device of claim 1, wherein the operations comprise obtaining a second group of attributes of malicious IP addresses from a second repository, wherein the determining of the third group of IP addresses comprises determining the third group of IP addresses from the second group of IP addresses as possible malicious IP addresses based on the second group of attributes.

### Claim 8 (depends on 1)

The device of claim 1, wherein the operations comprise generating a third group of attributes of malicious IP addresses, wherein the determining of the third group of IP addresses comprises determining the third group of IP addresses from the second group of IP addresses includes possible malicious IP addresses based on the third group of attributes.

### Claim 9 (depends on 8)

The device of claim 8, wherein the generating of the third group of attributes comprises generating the third group of attributes based on one of a statistical technique or hidden Markov-chains (HMM).

### Claim 10 (depends on 1)

The device of claim 1, wherein the determining of the third group of IP addresses comprises:
identifying a second IP address from the second group of IP addresses; and
determining that the second IP address is a possible malicious IP address based on a time-based graph associated with the second IP address.

### Claim 11 (depends on 1)

The device of claim 1, wherein the determining of the third group of IP addresses comprises:
identifying a third IP address from the second group of IP addresses and identifying a fourth IP address from the second group of IP addresses; and
determining that the third IP address and the fourth IP address are possible malicious IP addresses in response to determining the third IP address and the fourth IP address are associated with a fifth IP address from the group of IP addresses, wherein the fifth IP address is previously known to be malicious.

### Claim 12 (depends on 1)

The device of claim 1, wherein deep packet inspection is performed on one or more packets associated with the third group of IP addresses to determine the fourth group of IP addresses as possible malicious IP addresses.

### Claim 13

A non-transitory, machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
identifying a first group of Internet Protocol (IP) addresses;
determining a first portion of the first group of IP addresses from analyzing network flow traffic among the first group of IP addresses and one or more external IP addresses that includes possible malicious IP addresses utilizing a first machine learning application implementing a random forest model;
determining a second portion of the first group of IP addresses from analyzing network flow traffic among the first group of IP addresses and one or more external IP addresses that includes possible malicious IP addresses a second machine learning application implementing a deep learning model;
identifying a second group of IP addresses comprising the first portion of the first group of IP addresses and the second portion of the first group of IP addresses;
determining a group of attributes of malicious IP address;
identifying a third group of IP addresses from the second group of IP addresses for deep packet inspection based on the group of attributes;
receiving user-generated input indicating a fourth group of IP addresses from the third group of IP addresses includes possible malicious IP addresses, wherein packet analysis is performed on packets associated with the third group of IP addresses to determine the fourth group of IP addresses includes possible malicious IP addresses; and
transmitting a notification to a group of edge servers indicating that the fourth group of IP addresses includes possible malicious IP addresses.

### Claim 14 (depends on 13)

The non-transitory, machine-readable medium of claim 13, wherein the determining of the group of IP addresses comprises generating a group of rules from the group of attributes.

### Claim 15 (depends on 14)

The non-transitory, machine-readable medium of claim 14, wherein the generating of the group of rules comprises determining a group of attribute thresholds based on the group of attributes, wherein the group of rules comprises rules based on not satisfying each of the group of attribute thresholds.

### Claim 16 (depends on 13)

The non-transitory, machine-readable medium of claim 13, wherein the determining of the group of attributes comprise obtaining a first portion of the group of attributes from a repository.

### Claim 17 (depends on 13)

The non-transitory, machine-readable medium of claim 13, wherein the determining of the group of attributes comprise generating a second portion of group of attributes of malicious IP addresses.

### Claim 18 (depends on 17)

The non-transitory, machine-readable medium of claim 17, wherein the generating of the second portion of the group of attributes comprises generating the second portion of the group of attributes based on one of a statistical technique or hidden Markov-chains (HMM), wherein the packet analysis comprises deep packet inspection.

### Claim 19

A method, comprising:
identifying, by a processing system including a processor, a first group of Internet Protocol (IP) addresses;
determining, by the processing system, a second group of IP addresses from analyzing network flow traffic among the first group of IP addresses and one or more external IP addresses that includes possible malicious IP addresses utilizing a machine learning application implementing a plurality of machine learning models;
identifying, by the processing system, a third group of IP addresses from the second group of IP addresses includes possible malicious IP addresses for deep packet inspection based on time-based graph analysis of the second group of IP addresses;
receiving, by the processing system, user-generated input indicating a fourth group of IP addresses from the third group of IP addresses includes possible malicious IP addresses, wherein packet analysis is performed on packets associated with the third group of IP addresses to determine fourth group of IP addresses includes possible malicious IP addresses; and
transmitting, by the processing system, a notification to a group of communication devices indicating that the fourth group of IP addresses includes possible malicious IP addresses.

### Claim 20 (depends on 19)

The method of claim 19, wherein the plurality of machine learning models comprises a random forest model and a deep learning model, wherein the packet analysis comprises deep packet inspection.
