# US 2022/0036402 A1 · Detector, detection method, and detection program

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

- Number: US 2022/0036402 A1
- Document ID: US20220036402A1
- Status: Published application
- Kind: A1
- Application number: 17/278,673
- Filed: 2019-04-10
- Published: 2022-02-03
- Earliest claimed: 2018-09-25
- Assignees: Nippon Telegraph and Telephone Corporation
- Applicants: Nippon Telegraph and Telephone Corporation
- Inventors: Fumihiro KANEI; Daiki CHIBA; Yuta TAKATA; Mitsuaki AKIYAMA; Kunio HATO
- Web page: https://patentgrep.com/patent/US20220036402A1

## CPC

- G06Q 30/0241: Advertisements
- G06Q 30/0248: {Avoiding fraud}
- G06F 16/955: using information identifiers, e.g. uniform resource locators [URL]
- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- G06Q 30/0277: {Online advertisement}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A feature extraction unit extracts, from an advertising request to view an online advertisement, client information on a client as a transmission source of the advertising request and publisher information on a website of a publisher who displays advertising, and calculates a predetermined feature amount using the client information and the publisher information with respect to a plurality of advertising requests including at least a benign advertising request, and a determiner generation unit generates a determiner that determines whether an advertising request is malignant or not by using the calculated feature amount.

## Claims

### Claim 1

A detector comprising:
a memory; and
a processor coupled to the memory and programmed to execute a process comprising:
extracting, from an advertising request as a request to view an online advertisement, client information on a client as a transmission source of the advertising request and publisher information on a website of a publisher who displays an advertisement, and calculating a predetermined feature amount using the client information and the publisher information with respect to a plurality of advertising requests including at least a benign advertising request; and
generating a determiner that determines whether an advertising request is malignant or not by using the calculated feature amount.

### Claim 2 (depends on 1)

The detector according to claim 1, wherein the extracting, as the client information, information on a network to which an Internet protocol (IP) address of a transmission source of the advertising request belongs, and calculates the feature amount.

### Claim 3 (depends on 1)

The detector according to claim 1, wherein the extracting, as the client information, information on an operating environment of the client, and calculates the feature amount.

### Claim 4 (depends on 1)

The detector according to claim 1, wherein the extracting, as the publisher information, a domain name of a website of the publisher, and calculates the feature amount.

### Claim 5 (depends on 1)

The detector according to claim 1, wherein the calculating the feature amount by using appearance frequencies of the client information and the publisher information in the plurality of advertising requests.

### Claim 6

A detection method performed by a detector, the detection method comprising:
an extraction step of extracting, from an advertising request as a request to view an online advertisement, client information on a client as a transmission source of the advertising request and publisher information on a website of a publisher who displays advertising, and calculating a predetermined feature amount using the client information and the publisher information with respect to a plurality of advertising requests including at least a benign advertising request; and
a determiner generation step of generating a determiner that determines whether an advertising request is malignant or not by using the calculated feature amount.

### Claim 7

A non-transitory computer-readable recording medium including a detection program that causes a computer to execute:
an extraction step of extracting, from an advertising request as a request to view an online advertisement, client information on a client as a transmission source of the advertising request and publisher information on a website of a publisher who displays advertising, and calculating a predetermined feature amount using the client information and the publisher information with respect to a plurality of advertising requests including at least a benign advertising request; and
a determiner generation step of generating a determiner that determines whether an advertising request is malignant or not by using the calculated feature amount.
