View source for 17947667. COMPUTER AUTHENTICATION USING KNOWLEDGE OF FORMER DEVICES simplified abstract (Capital One Services, LLC)

=COMPUTER AUTHENTICATION USING KNOWLEDGE OF FORMER DEVICES=


==Organization Name==

[[:Category:Capital One Services, LLC|Capital One Services, LLC]]


[[Category:Capital One Services, LLC]]

==Inventor(s)==

[[:Category:Abdelkader M'Hamed Benkreira of Washington DC (US)|Abdelkader M'Hamed Benkreira of Washington DC (US)]][[Category:Abdelkader M'Hamed Benkreira of Washington DC (US)]]

[[:Category:Joshua Edwards of Philadelphia PA (US)|Joshua Edwards of Philadelphia PA (US)]][[Category:Joshua Edwards of Philadelphia PA (US)]]

[[:Category:Michael Mossoba of Great Falls VA (US)|Michael Mossoba of Great Falls VA (US)]][[Category:Michael Mossoba of Great Falls VA (US)]]

==COMPUTER AUTHENTICATION USING KNOWLEDGE OF FORMER DEVICES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17947667 titled 'COMPUTER AUTHENTICATION USING KNOWLEDGE OF FORMER DEVICES

==Simplified Explanation==

The patent application describes a method for improving computer authentication processes through machine learning models that analyze device reliability data to generate authentication questions for users.

* The computing device trains a machine learning model to assess device reliability data.
* A user requests access to an account, and the computing device uses the trained model to evaluate the reliability of devices associated with the account.
* Devices with reliability levels below a threshold value are excluded from the user's choices for authentication.
* An authentication question is generated based on the device reliability data, and access to the account is granted based on the user's response.

== Potential Applications ==
This technology could be applied in various industries where secure authentication is crucial, such as banking, healthcare, and government services.

== Problems Solved ==
This technology addresses the issue of unauthorized access to accounts by using device reliability data to enhance the authentication process and improve security.

== Benefits ==
The use of machine learning models to assess device reliability data can enhance the security of authentication processes, reduce the risk of unauthorized access, and provide a more seamless user experience.

== Potential Commercial Applications ==
This technology could be valuable for companies that prioritize data security and user authentication, such as financial institutions, healthcare providers, and government agencies.

== Possible Prior Art ==
One possible prior art could be the use of biometric authentication methods to enhance security in computer systems. 

=== What are the potential privacy implications of using device reliability data for authentication? ===

Using device reliability data for authentication could raise concerns about user privacy, as it involves analyzing and storing information about the devices used to access accounts. Companies implementing this technology would need to ensure that user data is protected and used responsibly.

=== How does this technology compare to traditional password-based authentication methods in terms of security and user experience? ===

This technology offers a more secure authentication process by considering device reliability data, which can be more difficult for unauthorized users to replicate compared to passwords. Additionally, it can provide a more seamless user experience by reducing the need for complex password requirements.


==Original Abstract Submitted==

Methods, systems, and apparatuses are described herein for improving computer authentication processes through computer-based authentication in a manner that uses knowledge of former devices. A computing device may train a machine learning model to output an indication of device reliability data associated with a particular device. The computing device may receive a request for access to an account from a user. The computing device may receive account data and provide the account data to the trained machine learning model. The computing device may receive data indicating device reliability for a set of devices from the machine learning model. The computing device may generate a modified set of device choices for the user by excluding devices having reliability levels below a threshold value. An authentication question may be generated, and access to the account may be provided based on a response to the authentication question.



[[Category:G06F21/34]]
[[Category:G06N20/00]]