公开(公告)号：US10776511B2

公开(公告)日：2020-09-15

申请号：US15805611

申请日：2017-11-07

Applicant: Apple Inc.

Inventor： Kevin W. Decker ,  Conrad Shultz ,  Steve Falkenburg ,  Mateusz Rajca ,  Abhishek Bhowmick ,  Andrew H. Vyrros ,  Umesh S. Vaishampayan

IPC: H04L29/06 ,  G06F21/62 ,  H04L9/32 ,  H04L29/08 ,  H04W12/02 ,  G06F3/0483 ,  G06F1/28 ,  G06F3/0482

Abstract: Embodiments described herein provide a privacy mechanism to protect user data when transmitting the data to a server that estimates a frequency of such data amongst a set of client devices. One embodiment uses a differential privacy mechanism to enhance a user experience by inferring potential user preferences from analyzing crowdsourced user interaction data. Based on a statistical analysis of user interactions in relation to various features or events, development efforts with respect to application behavior may be refined or enhanced. For example, user interactions in relation to the presentation of content such as content from online sources may be analyzed. Accordingly, presentation settings or preferences may be defined based on the crowdsourced user interaction data.

公开(公告)号：US10726139B2

公开(公告)日：2020-07-28

申请号：US15721894

申请日：2017-09-30

Applicant: Apple Inc.

Inventor： Abhishek Bhowmick ,  Andrew H. Vyrros ,  Matthew R. Salesi ,  Umesh S. Vaishampayan

IPC: G06F21/60 ,  G06F17/16 ,  G06F17/14 ,  G06F16/26 ,  H04L9/32 ,  G06F21/62 ,  G06F17/18

Abstract: Embodiments described herein ensure differential privacy when transmitting data to a server that estimates a frequency of such data amongst a set of client devices. The differential privacy mechanism may provide a predictable degree of variance for frequency estimations of data. The system may use a multibit histogram model or Hadamard multibit model for the differential privacy mechanism, both of which provide a predictable degree of accuracy of frequency estimations while still providing mathematically provable levels of privacy.

公开(公告)号：US10599867B2

公开(公告)日：2020-03-24

申请号：US15805591

申请日：2017-11-07

Applicant: Apple Inc.

Inventor： Abhishek Bhowmick ,  Andrew H. Vyrros ,  Umesh S. Vaishampayan ,  Kevin W. Decker ,  Conrad Shultz ,  Steve Falkenburg ,  Mateusz Rajca

IPC: H04L29/08 ,  G06F21/62 ,  H04L29/06 ,  G06F3/0483 ,  G06F1/28 ,  G06F3/0482

Abstract: Embodiments described herein provide a privacy mechanism to protect user data when transmitting the data to a server that estimates a frequency of such data amongst a set of client devices. In one embodiment, a differential privacy mechanism is implemented using a count-mean-sketch technique that can reduce resource requirements required to enable privacy while providing provable guarantees regarding privacy and utility. For instance, the mechanism can provide the ability to tailor utility (e.g. accuracy of estimations) against the resource requirements (e.g. transmission bandwidth and computation complexity).

公开(公告)号：US20180349620A1

公开(公告)日：2018-12-06

申请号：US15721894

申请日：2017-09-30

Applicant: Apple Inc.

Inventor： Abhishek Bhowmick ,  Andrew H. Vyrros ,  Matthew R. Salesi ,  Umesh S. Vaishampayan

IPC: G06F21/60 ,  G06F17/30 ,  G06F17/14 ,  G06F17/16

Abstract: Embodiments described herein ensure differential privacy when transmitting data to a server that estimates a frequency of such data amongst a set of client devices. The differential privacy mechanism may provide a predictable degree of variance for frequency estimations of data. The system may use a multibit histogram model or Hadamard multibit model for the differential privacy mechanism, both of which provide a predictable degree of accuracy of frequency estimations while still providing mathematically provable levels of privacy.

公开(公告)号：US11989634B2

公开(公告)日：2024-05-21

申请号：US16501132

申请日：2020-01-17

Applicant: Apple Inc.

Inventor： Abhishek Bhowmick ,  John Duchi ,  Julien Freudiger ,  Gaurav Kapoor ,  Ryan M. Rogers

IPC: G06F17/00 ,  G06N3/04 ,  G06N5/04 ,  G06N20/20

CPC classification number: G06N20/20 ,  G06N3/04 ,  G06N5/04

Abstract: Embodiments described herein provide for a non-transitory machine-readable medium storing instructions to cause one or more processors to perform operations comprising receiving a machine learning model from a server at a client device, training the machine learning model using local data at the client device, generating an update for the machine learning model, the update including a weight vector that represents a difference between the received machine learning model and the trained machine learning model, privatizing the update for the machine learning model, and transmitting the privatized update for the machine learning model to the server.

公开(公告)号：US11501008B2

公开(公告)日：2022-11-15

申请号：US16938741

申请日：2020-07-24

Applicant: Apple Inc.

Inventor： Abhishek Bhowmick ,  Andrew H. Vyrros ,  Matthew R. Salesi ,  Umesh S. Vaishampayan

IPC: G06F21/60 ,  G06F17/16 ,  G06F17/14 ,  G06F16/26 ,  H04L9/32 ,  G06F21/62 ,  G06F17/18

Abstract: Embodiments described herein ensure differential privacy when transmitting data to a server that estimates a frequency of such data amongst a set of client devices. The differential privacy mechanism may provide a predictable degree of variance for frequency estimations of data. The system may use a multibit histogram model or Hadamard multibit model for the differential privacy mechanism, both of which provide a predictable degree of accuracy of frequency estimations while still providing mathematically provable levels of privacy.

公开(公告)号：US11227063B2

公开(公告)日：2022-01-18

申请号：US17020637

申请日：2020-09-14

Applicant: Apple Inc.

Inventor： Abhishek Bhowmick ,  Andrew H. Vyrros ,  Umesh S. Vaishampayan ,  Kevin W. Decker ,  Conrad Shultz ,  Steve Falkenburg ,  Mateusz Rajca

IPC: H04L29/06 ,  G06F21/62 ,  H04L9/32 ,  H04L29/08 ,  H04W12/02 ,  G06F3/0483 ,  G06F1/28 ,  G06F3/0482

Abstract: Embodiments described herein provide a privacy mechanism to protect user data when transmitting the data to a server that estimates a frequency of such data amongst a set of client devices. In one embodiment, a differential privacy mechanism is implemented using a count-mean-sketch technique that can reduce resource requirements required to enable privacy while providing provable guarantees regarding privacy and utility. For instance, the mechanism can provide the ability to tailor utility (e.g. accuracy of estimations) against the resource requirements (e.g. transmission bandwidth and computation complexity).

公开(公告)号：US10599868B2

公开(公告)日：2020-03-24

申请号：US15805632

申请日：2017-11-07

Applicant: Apple Inc.

Inventor： Gavin Barraclough ,  Christophe Dumez ,  Abhishek Bhowmick ,  Andrew H. Vyrros ,  Umesh S. Vaishampayan

IPC: G06F7/04 ,  G06F21/62 ,  H04L29/06 ,  H04L9/32 ,  H04L29/08 ,  H04W12/02 ,  G06F3/0483 ,  G06F1/28 ,  G06F3/0482

Abstract: Embodiments described herein provide a privacy mechanism to protect user data when transmitting the data to a server that estimates a frequency of such data amongst a set of client devices. One embodiment uses a differential privacy mechanism to enhance a user experience by identifying particular websites that exhibit particular characteristics. In one embodiment, websites that are associated with a high resource consumption are identified. High resource consumption can be identified based on threshold of particular resources such as processor, memory, network bandwidth, and power usage.

公开(公告)号：US20180349638A1

公开(公告)日：2018-12-06

申请号：US15805632

申请日：2017-11-07

Applicant: Apple Inc.

Inventor： Gavin Barraclough ,  Christophe Dumez ,  Abhishek Bhowmick ,  Andrew H. Vyrros ,  Umesh S. Vaishampayan

IPC: G06F21/62 ,  H04L29/06 ,  G06F1/28

CPC classification number: G06F21/6245 ,  G06F1/28 ,  G06F3/0482 ,  G06F3/0483 ,  H04L9/3239 ,  H04L63/0428 ,  H04L67/02 ,  H04L67/22 ,  H04L2209/34 ,  H04L2209/42 ,  H04W12/02

Abstract: Embodiments described herein provide a privacy mechanism to protect user data when transmitting the data to a server that estimates a frequency of such data amongst a set of client devices. One embodiment uses a differential privacy mechanism to enhance a user experience by identifying particular websites that exhibit particular characteristics. In one embodiment, websites that are associated with a high resource consumption are identified. High resource consumption can be identified based on threshold of particular resources such as processor, memory, network bandwidth, and power usage.

公开(公告)号：US20180349637A1

公开(公告)日：2018-12-06

申请号：US15805611

申请日：2017-11-07

Applicant: Apple Inc.

Inventor： Kevin W. Decker ,  Conrad Shultz ,  Steve Falkenburg ,  Mateusz Rajca ,  Abhishek Bhowmick ,  Andrew H. Vyrros ,  Umesh S. Vaishampayan

IPC: G06F21/62 ,  G06F3/0483

Abstract: Embodiments described herein provide a privacy mechanism to protect user data when transmitting the data to a server that estimates a frequency of such data amongst a set of client devices. One embodiment uses a differential privacy mechanism to enhance a user experience by inferring potential user preferences from analyzing crowdsourced user interaction data. Based on a statistical analysis of user interactions in relation to various features or events, development efforts with respect to application behavior may be refined or enhanced. For example, user interactions in relation to the presentation of content such as content from online sources may be analyzed. Accordingly, presentation settings or preferences may be defined based on the crowdsourced user interaction data.