Browse Prior Art Database

A Method of Dynamic Identity Fraud Detection Disclosure Number: IPCOM000254896D
Publication Date: 2018-Aug-10
Document File: 6 page(s) / 272K

Publishing Venue

The Prior Art Database

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 39% of the total text.

A Method of Dynamic Identity Fraud Detection


This paper discusses a new way to proactively determine entity fraud problem in social

Apps based on social network entity identification with person’s identity analysis.


Data anonymization (DA) is a type of information sanitization whose intent is privacy

protection. It is the process of either encrypting or removing personally identifiable

information from data sets, so that the people whom the data describe remain

anonymous. And, artificial entities are widely used in the social network for protect

personal information. The use of a single identity for a given user across multiple

systems eases tasks for administrators and users. It simplifies access monitoring and

verification and allows the organization to minimize excessive privileges granted to one

user. User access can be tracked from initiation to termination of user access.

Named entity recognition and disambiguation (NERD) is a task of determining an

identity of entities mentioned in social network. In social media apps, there are different

methods to link the artificial entities to real identity. It is very important to identify a real

personal identity in 3rd party authentication on network banking.


Identity fraud is one of the serious internet criminals. Social interaction depends on

knowing with whom one is interacting. However, a critical problem in social network

is hard to knowing with whom one is interacting, because of following reasons:

• Anyone can add a “new friend” into a chatting group.

• A new added user without entity verification, but can easily add others as


• People spend a lot of time on mobile device for chatting and guessing social

network identities.

• People need more intelligent features guessing with whom one is interacting

via mobile Apps

• There are issues of privacy and security related to digital identity.

• It is risky to chat with social media identities without a right method to

associate and unify social media identities into a personal identity. For


Despite the fact that there are many authentication systems and digital identifiers that

try to address these problems, there is still a need for a centralized and verified

identification system. Therefore, it is necessary to define a method to solve the


Main Idea:

The main idea defines a method of dynamic identity fraud detection for solving

ambiguity on Personally identifiable information user photo, phone number, social

media account IDs ( (App1, ID1, User Remark-1, UserTag-1), (App2, ID-2 User

Remark-2, UserTag-2) , User(App-3, ID-3, User Remark-3, UserTag-3…). By using

the method, users can receive an automated contact list update service in real time.

The method is comprising of:

• creating a dynamic identity fraud detection [DIFD] framework for identifying and

tagging multiple social network identities.

• defining an ontology mapping data structure for holding identified social network