Paypal, Inc.

Abhishek Chhibber

Kishore Jaladi

Darshan Desai

Michael Charles Todasco

Nitin S Sharma

Sundar Amalan Vincent

Jeffrey Alan Edelen

Darshankumar Bhadrasinh Desai

Hari Hara Balan Shanmugasundaram

Oliver J Reyes

Lakshmikanth Raghavan

Vidyut Mukund Naware

Santhosh Jagadeesan

Nelson Eng

Techniques are disclosed in which a computing device repeatedly trains, using a stream of user data received at the computing device, a baseline model to generate a device-trained model, wherein the baseline model is trained at the computing device without providing user data included in the stream to a server computer system. In some embodiments, the computing device inputs, to the device-trained model, a set of characteristics associated with a user request received from a user of the computing device, wherein the device-trained model outputs a score for the user request. In some embodiments, the computing device transmits, to the server computer system, the score for the user request, wherein the transmitting includes requesting a decision for the user request. In some embodiments, the computing device performs an action associated with the user request in response to receiving a decision for the user request from the server computer system.

Edge device machine learning

Techniques are disclosed in which a computer system receives, from a plurality of user computing devices, a plurality of device-trained models and obfuscated sets of user data stored at the plurality of user computing devices, where the device-trained models are trained at respective ones of the plurality of user computing devices using respective sets of user data prior to obfuscation. In some embodiments, the server computer system determines similarity scores for the plurality of device-trained models, wherein the similarity scores are determined based on a performance of the device-trained models. In some embodiments, the server computer system identifies, based on the similarity scores, at least one of the plurality of device-trained models as a low-performance model. In some embodiments, the server computer system transmits, to the user computing device corresponding to the low-performance model, an updated model.

Federated machine learning management

Techniques are disclosed in which an edge user computing device pre-processes a stream of user data prior to using the stream of data to train a machine learning model at the edge device. The edge device receives the stream of user data, where the stream of data includes a first set of characteristics associated with the edge device and a second set of characteristics associated with a plurality of user requests received from a user of the edge device. The edge device repeatedly generates, using the stream of data, sets of pre-processed user data by performing pre-processing techniques on characteristics included in the stream of data. The edge device repeatedly trains, using the sets of pre-processed data, a baseline model to generate a device-trained model, where the baseline model is trained at the edge device without providing user data included in the stream of data to a server computer system.

Edge device representation learning

Techniques are disclosed in which a computer system receives a transaction request and uses a federated machine learning model to analyze the transaction request. A server computer system may generate a federated machine learning model and distribute portions of the federated machine learning models to other components of the computer system including a user device and/or edge servers. In various embodiments, various components of the computer system apply transaction request evaluation factors to the portions of the federated machine learning model to generate scores. The server computer system uses the scores to determine a response to the transaction request.

Device-side federated machine learning computer system architecture

Systems and methods are presented for implementing hacker traffic barriers for mitigating unauthorized account usage. A security system securely associates a primary trusted device with a user using encrypted tokens stored in an enclave within the primary trusted device, authorizes web browser authentication, and provides both intrinsic and explicit checks for unauthorized access to an account.

System and method for implementing hacker traffic barriers

Techniques are disclosed relating to a method that includes, in response to a request from a user to complete a secure transaction, determining, by a computer system, that a plurality of transaction options is available for completing the secure transaction. The method further includes generating, by the computer system, a plurality of authentication codes, each authentication code of the plurality corresponding to a respective one of the plurality of transaction options. Receiving a particular authentication code of the plurality of authentication codes from a computing device associated with the user causes a selection of a corresponding transaction option.

Data input using multi-factor authentication

Systems and methods for redirecting control of a process performed on a first application on a user device to another second application on the user device include receiving, through a controlling a process, a request to perform an action (e.g., user authentication). A determination may be made whether the second application is able to facilitate completion of the action (e.g. performing the authentication). Control of the process may then be redirected from the first application to the second application in order to complete the action.

Mobile device transaction authentication application redirection system

A self-updating system for defending against a cyberattack requests connected devices to solve a problem that is created in a random manner. The problems are created in a manner such that the system can determine whether the client device is being used as part of a cyberattack based on how the client device responds to the problems.

Cyberattack prevention system

Systems and methods for redirecting control of a process performed on a browser application on a user device accessing a web application to a native application on the user device include receiving, through a web application controlling a process, a request to perform an action (e.g., user authentication). A determination is made whether the request identifies a native application feature for completing the action that is preferable over a web application feature for completing the same action. In response to the action being determined to be completed by a native application feature, a determination is then made as to whether the native application feature is enabled by the native application. In response to determining the native application feature is enabled, control of the process is redirected from the web application to the native application such that the native application completes the action using the native application feature.

Aspects of the present disclosure involve a system and method for implementing hacker traffic barriers. The current disclosure presents a system and method that provides securely associates a primary trusted device with a user, authorizes web browser authentication, and provides both intrinsic and explicit checks for authorizing access to an account.

Growing community of inventors

Sunnyvale, CA, United States of America

Abhishek Chhibber