公开(公告)号：US12199956B2

公开(公告)日：2025-01-14

申请号：US18403339

申请日：2024-01-03

Applicant: Google LLC

Inventor： Badih Ghazi ,  Noah Zeger Golowich ,  Shanmugasundaram Ravikumar ,  Pasin Manurangsi ,  Ameya Avinash Velingker ,  Rasmus Pagh

IPC: H04L29/06 ,  G06N5/04 ,  G06N20/00 ,  H04L9/40 ,  H04L9/06 ,  H04L9/08

Abstract: An encoding method for enabling privacy-preserving aggregation of private data can include obtaining private data including a private value, determining a probabilistic status defining one of a first condition and a second condition, producing a multiset including a plurality of multiset values, and providing the multiset for aggregation with a plurality of additional multisets respectively generated for a plurality of additional private values. In response to the probabilistic status having the first condition, the plurality of multiset values is based at least in part on the private value, and in response to the probabilistic status having the second condition, the plurality of multiset values is a noise message. The noise message is produced based at least in part on a noise distribution that comprises a discretization of a continuous unimodal distribution supported on a range from zero to a number of multiset values included in the plurality of multiset values.

公开(公告)号：US20210243171A1

公开(公告)日：2021-08-05

申请号：US17122638

申请日：2020-12-15

Applicant: Google LLC

Inventor： Badih Ghazi ,  Noah Zeger Golowich ,  Shanmugasundaram Ravikumar ,  Pasin Manurangsi ,  Ameya Avinash Velingker ,  Rasmus Pagh

IPC: H04L29/06 ,  G06N20/00 ,  G06N5/04

Abstract: An encoding method for enabling privacy-preserving aggregation of private data can include obtaining private data including a private value, determining a probabilistic status defining one of a first condition and a second condition, producing a multiset including a plurality of multiset values, and providing the multiset for aggregation with a plurality of additional multisets respectively generated for a plurality of additional private values. In response to the probabilistic status having the first condition, the plurality of multiset values is based at least in part on the private value, and in response to the probabilistic status having the second condition, the plurality of multiset values is a noise message. The noise message is produced based at least in part on a noise distribution that comprises a discretization of a continuous unimodal distribution supported on a range from zero to a number of multiset values included in the plurality of multiset values.

公开(公告)号：US12072987B1

公开(公告)日：2024-08-27

申请号：US17227532

申请日：2021-04-12

Applicant: Google LLC

Inventor： Pasin Manurangsi ,  Badih Ghazi ,  Shanmugasundaram Ravikumar ,  Rasmus Pagh ,  Amer Sinha

IPC: G06F21/60 ,  G06N20/00

CPC classification number: G06F21/60 ,  G06N20/00

Abstract: The present disclosure provides practical communication-efficient and low-error algorithms for aggregation of private data. For example, the proposed algorithms can be implemented in the shuffled DP model. Specific example operations that can be performed using the proposed algorithms include summation (e.g., binary summation, integer summation) and histograms over a moderate number of buckets. The proposed algorithms achieve accuracy that is arbitrarily close to that of central DP algorithms with an expected communication per user essentially matching what is needed without any privacy constraints.

公开(公告)号：US11902259B2

公开(公告)日：2024-02-13

申请号：US17122638

申请日：2020-12-15

Applicant: Google LLC

Inventor： Badih Ghazi ,  Noah Zeger Golowich ,  Shanmugasundaram Ravikumar ,  Pasin Manurangsi ,  Ameya Avinash Velingker ,  Rasmus Pagh

IPC: H04L29/06 ,  H04L9/40 ,  G06N5/04 ,  G06N20/00 ,  H04L9/06 ,  H04L9/08

CPC classification number: H04L63/0428 ,  G06N5/04 ,  G06N20/00

Abstract: An encoding method for enabling privacy-preserving aggregation of private data can include obtaining private data including a private value, determining a probabilistic status defining one of a first condition and a second condition, producing a multiset including a plurality of multiset values, and providing the multiset for aggregation with a plurality of additional multisets respectively generated for a plurality of additional private values. In response to the probabilistic status having the first condition, the plurality of multiset values is based at least in part on the private value, and in response to the probabilistic status having the second condition, the plurality of multiset values is a noise message. The noise message is produced based at least in part on a noise distribution that comprises a discretization of a continuous unimodal distribution supported on a range from zero to a number of multiset values included in the plurality of multiset values.

公开(公告)号：US20220374542A1

公开(公告)日：2022-11-24

申请号：US17620438

申请日：2020-06-17

Applicant: Google LLC

Inventor： Badih Ghazi ,  Rasmus Pagh ,  Ameya Velingker

IPC: G06F21/62

Abstract: An encoding process performed by a computing device (e.g., a user's private device) can include obtaining private data that includes a private value. According to an aspect of the present disclosure, the computing device can produce a plurality of messages that respectively comprise a plurality of message values, where a total sum of the plurality of message values approximates the private value, and where at least one of the plurality of message values is randomly selected. The device can provide the plurality of messages for aggregation with a plurality of additional messages respectively generated for a plurality of additional private values. For example, the messages can be transmitted to a shuffler model configured to shuffle the plurality of messages with the plurality of additional messages.

公开(公告)号：US12248604B2

公开(公告)日：2025-03-11

申请号：US17620438

申请日：2020-06-17

Applicant: Google LLC

Inventor： Badih Ghazi ,  Rasmus Pagh ,  Ameya Velingker

IPC: G06F21/62

Abstract: An encoding process performed by a computing device (e.g., a user's private device) can include obtaining private data that includes a private value. According to an aspect of the present disclosure, the computing device can produce a plurality of messages that respectively comprise a plurality of message values, where a total sum of the plurality of message values approximates the private value, and where at least one of the plurality of message values is randomly selected. The device can provide the plurality of messages for aggregation with a plurality of additional messages respectively generated for a plurality of additional private values. For example, the messages can be transmitted to a shuffler model configured to shuffle the plurality of messages with the plurality of additional messages.

公开(公告)号：US12175383B2

公开(公告)日：2024-12-24

申请号：US17320924

申请日：2021-05-14

Applicant: Google LLC

Inventor： Rasmus Pagh

IPC: G06N5/04 ,  G06N20/00 ,  H03M7/24 ,  H03M7/30

Abstract: A computer-implemented method of compressing floating point data of a machine-learned model into a compressed representation of the floating point data can include obtaining floating point data including a plurality of machine-learned model parameters encoded as a tensor, determining a sign vector including a sign bit of each of the plurality of machine-learned model parameters, determining a normalization exponent based on the floating point data, determining a plurality of offsets descriptive of a difference between an exponent of the machine-learned model parameters and the normalization exponent, determining a bitmap including a unary representation of the plurality of offsets, determining a plurality of adjusted mantissas based at least in part on the plurality of offsets, and storing a compressed representation of the floating point data, the compressed representation including the sign vector, the normalization exponent, the bitmap, and one or more bits of each of the plurality of adjusted mantissas.

公开(公告)号：US20240236052A1

公开(公告)日：2024-07-11

申请号：US18403339

申请日：2024-01-03

Applicant: Google LLC

Inventor： Badih Ghazi ,  Noah Zeger Golowich ,  Shanmugasundaram Ravikumar ,  Pasin Manurangsi ,  Ameya Avinash Velingker ,  Rasmus Pagh

IPC: H04L9/40 ,  G06N5/04 ,  G06N20/00

CPC classification number: H04L63/0428 ,  G06N5/04 ,  G06N20/00

Abstract: An encoding method for enabling privacy-preserving aggregation of private data can include obtaining private data including a private value, determining a probabilistic status defining one of a first condition and a second condition, producing a multiset including a plurality of multiset values, and providing the multiset for aggregation with a plurality of additional multisets respectively generated for a plurality of additional private values. In response to the probabilistic status having the first condition, the plurality of multiset values is based at least in part on the private value, and in response to the probabilistic status having the second condition, the plurality of multiset values is a noise message. The noise message is produced based at least in part on a noise distribution that comprises a discretization of a continuous unimodal distribution supported on a range from zero to a number of multiset values included in the plurality of multiset values.

公开(公告)号：US20210357789A1

公开(公告)日：2021-11-18

申请号：US17320924

申请日：2021-05-14

Applicant: Google LLC

Inventor： Rasmus Pagh

IPC: G06N5/04 ,  G06N20/00

Abstract: A computer-implemented method of compressing floating point data of a machine-learned model into a compressed representation of the floating point data can include obtaining floating point data including a plurality of machine-learned model parameters encoded as a tensor, determining a sign vector including a sign bit of each of the plurality of machine-learned model parameters, determining a normalization exponent based on the floating point data, determining a plurality of offsets descriptive of a difference between an exponent of the machine-learned model parameters and the normalization exponent, determining a bitmap including a unary representation of the plurality of offsets, determining a plurality of adjusted mantissas based at least in part on the plurality of offsets, and storing a compressed representation of the floating point data, the compressed representation including the sign vector, the normalization exponent, the bitmap, and one or more bits of each of the plurality of adjusted mantissas.