公开(公告)号：US11113776B1

公开(公告)日：2021-09-07

申请号：US16541961

申请日：2019-08-15

Applicant: Google LLC

Inventor： Gang Wang ,  Matthew Young-Lai ,  Zoltan Szamonek

IPC: G06Q30/00 ,  G06Q50/26 ,  G06Q30/02 ,  G06F21/62

Abstract: A computer-implemented method for protecting user identity within online content providing environments uses a security content management system (CMS) including at least one processor and a memory. The method includes identifying a request for an online content item associated with an online device. The online device is associated with actual device data. The method also includes determining a first characteristic value associated with the actual device data of the online device. The method further includes generating, by the processor, substitute device data. The substitute device data represents at least the first characteristic value. The method also includes providing the substitute device data to an online content provider.

公开(公告)号：US11093644B2

公开(公告)日：2021-08-17

申请号：US16412027

申请日：2019-05-14

Applicant: Google LLC

Inventor： Jonathan Krafcik ,  Gang Wang ,  Yibo Chen

IPC: G06F21/62 ,  G06N20/00 ,  G06N5/04

Abstract: The present disclosure provides systems and methods for automatically detecting third-party re-identification of anonymized computing devices. The method includes retrieving a log of content items provided to anonymized computing devices identifying a first content item provided to a plurality of anonymized computing devices within a first predetermined time period; for each anonymized computing device of the plurality of anonymized computing devices, generating a set of identifications of second content items retrieved by the anonymized computing device prior to receiving the first content item within a second predetermined time period; determining that signals or combinations of signals with a highest predictive ability between a first set of identifications and a second set of identifications exceeds a threshold; identifying a provider of the first content item; and if the signals or combinations of signals with the highest predictive ability exceeds the threshold, preventing, transmission of a request of an anonymized computing device for a content item to the identified provider.

公开(公告)号：US20210240854A1

公开(公告)日：2021-08-05

申请号：US17042785

申请日：2019-04-16

Applicant: Google LLC

Inventor： Jonathan Krafcik ,  Yian Gao ,  Gang Wang

IPC: G06F21/62 ,  H04L29/08

Abstract: Systems and methods described herein can provide a restricted environment for the local execution of server provided processor-executable instructions. The restricted environment can be maintained by a web browser to enable sandboxed generation of content requests by the web browser during the rendering of web pages. The restricted environment can enable the web browser to control the generation and transmission of content requests.

公开(公告)号：US11082501B2

公开(公告)日：2021-08-03

申请号：US16855952

申请日：2020-04-22

Applicant: Google LLC

Inventor： Gang Wang ,  Sagnik Nandy

IPC: G06F15/16 ,  H04L29/08 ,  H04L29/06 ,  H04L12/743

Abstract: The systems and methods described herein can enable the indirect transmission of session data between different domains. The system can pass the session data through a hashing function so that the data from a given domain remains private and secure to the specific domain. The system can generate clusters of associated domains for a given client device that the system can use to maintain a session between the client device and the domain.

公开(公告)号：US20210075614A1

公开(公告)日：2021-03-11

申请号：US16757835

申请日：2019-09-03

Applicant: Google LLC

Inventor： Gang Wang ,  Marcel M. Moti Yung

IPC: H04L9/32 ,  G06F16/951

Abstract: The present disclosure provides systems and methods for secure identification retrieval. The method includes retrieving a value of a periodic variable and calculating a plurality of query tokens from a corresponding plurality of client device identifiers and the value of the periodic variable. Each query token is associated with a corresponding client device identifier in a first database. The method further includes receiving a first query token calculated from a client device identifier of the first client device and the value of the periodic variable and identifying a second query token of the calculated plurality of query tokens in the first database matching the first query token. The method further includes, responsive to the identification, retrieving the associated client device identifier and retrieving one or more characteristics of the first client device according to the associated client device identifier. The method further includes transmitting the retrieved one or more characteristics.

公开(公告)号：US20200344058A1

公开(公告)日：2020-10-29

申请号：US16553599

申请日：2019-08-28

Applicant: Google LLC

Inventor： Zhong Wang ,  Gang Wang

IPC: H04L9/32 ,  H04L9/08

Abstract: At least one aspect is directed to improving the performance of real-time verification of online identity. The issuer computing system can receive a request to generate a composite token, the composite token configured to authorize certain verifying parties to authenticate a first-party token comprising information about a client. The issuer can generate a composite token using cryptographic keys and distribute it to the client, who can distribute it to other content item networks. The verifying parties can receive the composite token from the content item networks, use a cryptographic key verify the authenticity of the token corresponding to the client device, and use the token to further process content item operations. The system can distribute the cryptographic keys prior to the generation and verification of the composite token, and as such allow the parties to verify the composite token in real-time without contacting outside verification parties.

公开(公告)号：US20190318394A1

公开(公告)日：2019-10-17

申请号：US16455948

申请日：2019-06-28

Applicant: Google LLC

Inventor： Gang Wang ,  Yong Yao

IPC: G06Q30/02 ,  G06F21/62

Abstract: Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium for providing content. A method includes: receiving a first request for filling a slot on a first publisher page, the request including an encrypted publisher cookie; providing content responsive to the request; upon receipt of an indication that a user interacted with the content, creating and providing a content serving system cookie; linking the received encrypted publisher cookie with the content serving system cookie; receiving a second, different request for content in association with rendering a second, different publisher page, the second, different request including an encrypted publisher cookie associated with the second different publisher page and the previously provided content serving system cookie; linking the received encrypted publisher cookie associated with the second, different publisher page with the encrypted publisher cookie associated with the first publisher page; and using the linkings to determine content to deliver.

公开(公告)号：US20190149625A1

公开(公告)日：2019-05-16

申请号：US15812130

申请日：2017-11-14

Applicant: Google LLC

Inventor： Haskell Aaron Garon ,  Nicholas Wildman Isaacs ,  Gang Wang

IPC: H04L29/08 ,  G06F17/30

Abstract: Methods, systems, and computer readable medium for improving opt-out compliance are disclosed. A method includes identifying an opportunity to transmit a digital component to a client device that is identified by a given unique identifier, accessing a database, identifying, within the database and based on the accessing, an opt-out timestamp specifying when a given user corresponding to the given unique identifier was presented the opt-out opportunity, determining, whether the timestamp indicates that the user was presented with the opportunity within a specified amount of time, and processing the opportunity by submitting the opportunity to transmit the digital component to third party digital component sources in response to determining that the given user was presented with the opportunity within the specified amount of time, or refraining from submitting the opportunity in response to determining that the given user was not presented with the opportunity within the specified amount of time.

公开(公告)号：US20250167988A1

公开(公告)日：2025-05-22

申请号：US18960831

申请日：2024-11-26

Applicant: Google LLC

Inventor： Gang Wang ,  Ardian Poernomo ,  Marcel M. Moti Yung

IPC: H04L9/08 ,  G06F21/62 ,  G06Q10/10 ,  G06Q30/0241 ,  H04L9/06

Abstract: This disclosure relates to protecting the security of information in content selection and distribution. In one aspect, a method includes receiving, from a client device and by a first computing system of multi-party computation (MPC) systems, a digital component request including first secret shares of data identifying user groups that include a user of the client device as a member. The first computing system transmits a contextual digital component request to a content platform. The first computing system receives, from the content platform, selection data for multiple digital components. The selection data includes first vector data defining a contextual-based vector of values selected based in part on the set of contextual signals. The first computing system obtains, for each digital component, second vector data defining a user group-based vector of values selected based in part on a respective user group corresponding to the digital component.

公开(公告)号：US12282867B2

公开(公告)日：2025-04-22

申请号：US17927923

申请日：2021-09-29

Applicant: Google LLC

Inventor： Gang Wang ,  Marcel M. Moti Yung

IPC: G06N5/04 ,  G06F18/2413 ,  G06F21/60

Abstract: This disclosure relates to a privacy preserving machine learning platform. In one aspect, a method includes receiving, by a first computing system of multiple multi-party computation (MPC) systems, an inference request that includes a first share of a given user profile. A number k of nearest neighbor user profiles that are considered most similar to the given user profile are identified. The first computing system identifies a first set of nearest neighbor profiles based on the first share of the given user profile and a k-nearest neighbor model. The first computing system receives, from each of one or more second computing systems of the multiple MPC systems, data indicating a respective second set of nearest neighbor profiles identified by the second computing system based on a respective second share of the given user profile and a respective second k-nearest neighbor model trained by the second computing system.