公开(公告)号：US20240211965A1

公开(公告)日：2024-06-27

申请号：US18086387

申请日：2022-12-21

Applicant: Stripe, Inc.

Inventor： Massoud Hosseinali ,  Florian Hartl ,  Efstathios Vafeias ,  Keagan Long ,  Stef Nelson-Lindall ,  Dan Brown

IPC: G06Q30/018 ,  G06F18/23213

CPC classification number: G06Q30/0185 ,  G06F18/23213 ,  G06N20/20

Abstract: A method and apparatus for detecting fraudulent merchant activities at a commerce platform system are described. The method may include accessing signal data for a merchant system generated for one or more merchant system transactions processed by a commerce platform system, encoding the signal data into a plurality of sets of input signals, and inputting a first set of input signals into a first machine learning model to generate a fraud score from the first set of input signals. The method may also include performing clustering of the merchant system using a second set of input signals to cluster the merchant system with zero or more additional merchant systems in one of a plurality of different merchant system cohort clusters, and generating cluster fraud scores. In response to detecting that a cluster fraud score for a cluster into which the merchant system was assigned satisfies a cohort cluster fraud threshold, the method may include taking an action against each merchant system in the cluster.

公开(公告)号：US20240211845A1

公开(公告)日：2024-06-27

申请号：US18145633

申请日：2022-12-22

Applicant: Stripe, Inc.

Inventor： Daniel SIM ,  Donald Vitas M. PIRET ,  Shengwei WU

IPC: G06Q10/0639 ,  G06N20/00

CPC classification number: G06Q10/06395 ,  G06N20/00

Abstract: Disclosed herein are systems and methods for identifying and transmitting electronic requests to a suitable service provider. In one method, a server receives, from a computing device, a request to verify data via at least one service provider; executes a first computer model to identify a likelihood of verification success of the data; responsive to the likelihood of verification success satisfying a threshold, executes a second computer model to determine a service provider to transmit the request based on a first attribute associated with the data, a type of verification associated with the request, and a second attribute associated with the set of service providers and an impact value associated with each service provider; and responsive to determining the service provider from the set of service providers, transmitting, by the processor via an application programming interface, the data to the service provider.

公开(公告)号：US20240193595A1

公开(公告)日：2024-06-13

申请号：US18444568

申请日：2024-02-16

Applicant: Stripe, Inc.

Inventor： Michael David DAHN ,  Bryan Daniel BERG

IPC: G06Q20/38

CPC classification number: G06Q20/3829 ,  G06Q2220/10

Abstract: The subject technology enables encryption key distribution when a processor is in offline mode. When offline, key distribution servers can distribute private/public key pairs in place of the processor. The servers can distribute a public key to a user device for encryption of data. The encrypted data can be provided to the processor, which can return a token in response to provide to the first server.

公开(公告)号：US12002054B1

公开(公告)日：2024-06-04

申请号：US18071381

申请日：2022-11-29

Applicant: Stripe, Inc.

Inventor： Charlotte Gils ,  Efstathios Vafeias

IPC: G06Q40/00 ,  G06Q20/40 ,  G06V10/774 ,  G06V10/82 ,  G06V20/00 ,  G06V30/41

CPC classification number: G06Q20/4016 ,  G06V10/774 ,  G06V10/82 ,  G06V20/95 ,  G06V30/41

Abstract: A method and apparatus for fraud detection during transactions using identity graphs are described. The method may include receiving a document image for detecting whether an identity document depicted within the document image is fraudulent. The method may also include extracting data associated with the document image to generate extracted data. The method may also include processing, by a single machine learning model, subsets of the decoded image data used as corresponding inputs to each of a set of machine learning model backbones of the single machine learning model that generate one or more intermediate signals indicative of whether a subset of the extracted image data input into said each machine learning model backbone is associated with a fraudulent identity document. The method may also include processing, by a second machine learning model backbone that generates a final score indicative of whether the document image depicts a fraudulent identity document, at least one or more intermediate signals.

公开(公告)号：US20240168786A1

公开(公告)日：2024-05-23

申请号：US17990514

申请日：2022-11-18

Applicant: STRIPE, INC.

Inventor： Sushain Cherivirala ,  Andrew Dunham

IPC: G06F9/455 ,  G06F8/41

CPC classification number: G06F9/45558 ,  G06F8/433 ,  G06F2009/45575 ,  G06F2009/45583

Abstract: Examples of the present disclosure describe systems and methods for a remotebuild snapshot storage volume. In some examples, a system may include a virtual machine (VM). The VM may be configured to mount a snapshot storage volume. The snapshot storage volume may store a set of build dependencies. The VM may also be configured to execute a software build workflow using the set of build dependencies stored within the snapshot storage volume and produce a software build action result of the software build workflow.

公开(公告)号：US20240168733A1

公开(公告)日：2024-05-23

申请号：US17990370

申请日：2022-11-18

Applicant: STRIPE, INC.

Inventor： Sushain Cherivirala ,  Ainsley Escorce-Jones

IPC: G06F8/41 ,  G06F12/0815 ,  G06F16/14 ,  G06F16/172 ,  G06F16/185

CPC classification number: G06F8/433 ,  G06F12/0815 ,  G06F16/152 ,  G06F16/172 ,  G06F16/185

Abstract: A cached parent node of a remotebuild tree cache may be identified in a cache associated with a parent node of a file system. The cache may be configured to store a plurality of cached traversal results, and each may be associated with a corresponding node of the file system. The parent node may be associated with a project root of the file system. A current hash value of the parent node may be compared with a cached hash value of the cached parent node. In response to determining that the cache is stale based on the current hash value and the cached hash value not matching, the cache may be updated by traversing a set of descendent nodes of the parent node based upon the cache miss and updating the cached parent node with a traversal result and with the current hash value of the parent node.

公开(公告)号：US11989633B2

公开(公告)日：2024-05-21

申请号：US16258116

申请日：2019-01-25

Applicant: Stripe, Inc.

Inventor： Ashish Goel ,  Peter Lofgren

IPC: G06N20/20 ,  G06F18/243 ,  G06N3/084 ,  G06N5/043

CPC classification number: G06N20/20 ,  G06F18/24323 ,  G06N3/084 ,  G06N5/043

Abstract: Embodiments herein use transfer learning paradigms to facilitate classification across entities without requiring the entities access to the other party's sensitive data. In one or more embodiments, one entity may train a model using its own data (which may include at least some non-shared data) and shares either the scores (or an intermediate representation of the scores). One or more other parties may use the scores as a feature in its own model. The scores may be considered to act as an embedding of the features but do not reveal the features. In other embodiments, parties may be used to train part of a model or participate in generating one or more nodes of a decision tree without revealing all its features. The trained models or decision trees may then be used for classifying unlabeled events or items.

公开(公告)号：US20240152899A1

公开(公告)日：2024-05-09

申请号：US17983895

申请日：2022-11-09

Applicant: Stripe, Inc.

Inventor： Jack DeLoach ,  Mark Fielbig ,  Nicole DeBickes ,  Vinay Padma ,  Rustem Muslimov ,  Atul Bhatia ,  Shanshan Chen ,  Michael Shafrir ,  Nate Barnett

IPC: G06Q20/32 ,  G06F9/54 ,  G06Q20/12

CPC classification number: G06Q20/3267 ,  G06F9/54 ,  G06Q20/123

Abstract: The present disclosure is directed to handling communication, including handoffs, between applications on a payment terminal. In some embodiments, a method comprises: receiving, by the first mobile application, a first request from a user to conduct a transaction via the first mobile application and transitioning control from the first mobile application to a second mobile application running on the mobile device to collect a payment for the transaction being processed by the first mobile application in response to receiving the first request to conduct a transaction. Subsequently, after processing the payment for the transaction, the method includes transitioning control back to the first mobile application from the second mobile application as part of sending an indication of results of processing the payment by the second mobile application.

公开(公告)号：US11966908B2

公开(公告)日：2024-04-23

申请号：US17871478

申请日：2022-07-22

Applicant: Stripe, Inc.

Inventor： Yue Bu

IPC: G06Q20/32 ,  G06Q20/38

CPC classification number: G06Q20/325 ,  G06Q20/385

Abstract: Methods, systems, and computer readable medium are provided for generating, by a secure processor, a plurality of configurable data entry elements configured into a webpage, receiving sensitive data entered via the plurality of configurable data entry elements during a user data entry session, generating a hidden controller iframe in the webpage, aggregating, by the hidden controller iframe, the sensitive data across the plurality of configurable data entry elements, and directing aggregated sensitive data to the secure processor hosted by a first server separate from a second server hosting the webpage.

公开(公告)号：US20240119538A1

公开(公告)日：2024-04-11

申请号：US18528437

申请日：2023-12-04

Applicant: Stripe, Inc.

Inventor： Robert Ying ,  Cale Horeff ,  Miguel Flores ,  Jeremiah Clemenson ,  Andy Zhang

IPC: G06Q40/12 ,  G06F16/23 ,  G06F16/901 ,  G06Q10/107 ,  G06Q20/40 ,  G06Q30/018 ,  G06Q40/02

CPC classification number: G06Q40/12 ,  G06F16/2379 ,  G06F16/9024 ,  G06Q10/107 ,  G06Q20/405 ,  G06Q30/0185 ,  G06Q40/02

Abstract: A method and apparatus is described for performing transaction tracing. The method may include mapping one or more funds flow transactions into each account to one or more funds flow transactions out of said each account based on a first-in-first-out ordering. The method may also include generating an initial graph from the mappings of the transactions for each said account. Furthermore, the method may include transforming the initial graph to a function graph, wherein the functional graph is a directed pseudoforest where each node has an out degree of at most one. Then, the method may include for a node in the functional graph, performing a trace of the transaction generating a set of transactions that contributed to the transaction.