公开(公告)号：US20250131112A1

公开(公告)日：2025-04-24

申请号：US18684996

申请日：2023-07-14

Applicant: Google LLC

Inventor： Pasin Manurangsi ,  Badih Ghazi ,  Shanmugasundaram Ravikumar ,  Jelani Osei Nelson

IPC: G06F21/62

Abstract: In one aspect, there is provided a method performed by one or more computers that includes: obtaining access data for a digital resource, access data including data identifying a set of users that accessed the digital resource at a time point, processing the access data to generate data defining a tree model, where each node in the tree model is associated with: (i) a key that specifies time intervals in the time span, and (ii) a value that is based on a respective number of users that satisfy a node-specific selection, receiving a request to determine a number of users that accessed the digital resource at least a predefined number of times within a time window, and in processing the tree model to generate an estimate for the number of users that accessed the digital resource at least the predefined number of times within the time window.

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：US11928159B2

公开(公告)日：2024-03-12

申请号：US17204546

申请日：2021-03-17

Applicant: Google LLC

Inventor： Shanmugasundaram Ravikumar ,  Pasin Manurangsi ,  Badih Ghazi

IPC: G06F16/906 ,  G06F18/21 ,  G06F18/214 ,  G06F18/23213 ,  G06F18/2413

CPC classification number: G06F16/906 ,  G06F18/214 ,  G06F18/2193 ,  G06F18/23213 ,  G06F18/24137

Abstract: Example techniques are provided for the task of differentially private clustering. For several basic clustering problems, including Euclidean DensestBall, 1-Cluster, k-means, and k-median, the present disclosure provides efficient differentially private algorithms that achieve essentially the same approximation ratios as those that can be obtained by any non-private algorithm, while incurring only small additive errors. This improves upon existing efficient algorithms that only achieve some large constant approximation factors.

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：US20220300558A1

公开(公告)日：2022-09-22

申请号：US17204546

申请日：2021-03-17

Applicant: Google LLC

Inventor： Shanmugasundaram Ravikumar ,  Pasin Manurangsi ,  Badih Ghazi

IPC: G06F16/906 ,  G06K9/62

Abstract: Example techniques are provided for the task of differentially private clustering. For several basic clustering problems, including Euclidean DensestBall, 1-Cluster, k-means, and k-median, the present disclosure provides efficient differentially private algorithms that achieve essentially the same approximation ratios as those that can be obtained by any non-private algorithm, while incurring only small additive errors. This improves upon existing efficient algorithms that only achieve some large constant approximation factors.

公开(公告)号：US20220129760A1

公开(公告)日：2022-04-28

申请号：US17511448

申请日：2021-10-26

Applicant: Google LLC

Inventor： Shanmugasundaram Ravikumar ,  Badih Ghazi ,  Pasin Manurangsi ,  Chiyuan Zhang ,  Noah Golowich

IPC: G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training neural networks with label differential privacy. One of the methods includes, for each training example: processing the network input in the training example using the neural network in accordance with the values of the network parameters as of the beginning of the training iteration to generate a network output, generating a private network output for the training example from the target output in the training example and the network output for the training example, and generating a modified training example that includes the network input in the training example and the private network output for the training example; and training the neural network on at least the modified training examples to update the values of the network parameters.