Apple Inc.

Layer, Inc.

Andrew H Vyrros

Justin N Wood

Umesh Suresh Vaishampayan

Justin Edward Santamaria

Patrick G Gates

Gaurav Kapoor

Abhradeep Guha Thakurta

Jeremy Matthew Werner

Abhishek Bhowmick

Joe S Abuan

Daniel Ben Pollack

Vipul Ved Prakash

Julien F Freudiger

Arnaud Legendre

Jeffrey Thomas Davey

Darryl Neil Bleau

Arun Godfrey Mathias

Dylan Ross Edwards

Kevin W Decker

Matthew Scott Klahn

Conrad A Shultz

Jeremy Brown

Jonathan E Drummond

Hyeonkuk Jeong

Roberto Garcia

Steven J Falkenburg

Steven Duplinsky

Vivek Rangarajan Sridhar

Doug Davidson

Julien Freudinger

Braden Jacob Thomas

Mateusz Rajca

Steve Falkenburg

Matthew Elliott Shepherd

Greg Novick

Pierre De Filippis

Drew Yao

Berkat S Tung

Amit K Vyas

Jonathan Jay Andrews

Anand Ramadurai

Ryan M Rogers

Richard Frederick Wagner

Lee Russell

Philip Smith

Matthew R Salesi

Naveen Nalam

Alexander A Medina

Matthew Elliot Shepherd

David Michael Chan

Conrad Sauerwald

Gokul P Thirumalai

Giulia Maria Pagallo

Jeremy A Wyld

Roberto Garcia, Jr

Kit-Man Wan

Thomas P Devanneaux

Gavin Barraclough

Phillip Stanley-Marbell

Amol V Pattekar

Andrew Robert Byde

Dan Keen

Daniel D Schucker

Mitch Adler

Erik Strahm

David B Myszewski

William T Duffy

Justin M N Wood

Brittany D Hughes

Christophe Dumez

John Andrew McCulloh

Yannis Minadakis

Ron Palmeri

Tomaz Stolfa

Don Fletcher

Eric Danforth Strahm

Lon Hardeman

Selva Subramaniam

Rakesh Singh

Sudipt Sinha

Josh Converse

Christophe P Dumez

Mateusz K Rajca

Darryl N Bleau

Jeffrey T Davey

Justin MN Wood

Natthew Klahn

Embodiments described herein provide a technique to crowdsource labeling of training data for a machine learning model while maintaining the privacy of the data provided by crowdsourcing participants. Client devices can be used to generate proposed labels for a unit of data to be used in a training dataset. One or more privacy mechanisms are used to protect user data when transmitting the data to a server. The server can aggregate the proposed labels and use the most frequently proposed labels for an element as the label for the element when generating training data for the machine learning model. The machine learning model is then trained using the crowdsourced labels to improve the accuracy of the model.

Distributed labeling for supervised learning

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.

Differential privacy using a multibit histogram

Embodiments described herein enable data associated with a large plurality of users to be analyzed without compromising the privacy of the user data. In one embodiment, a user can opt-in to allow analysis of clear text of the user's emails. An analysis process can then be performed in which an analysis service receives clear text of an email of a client device; processes the clear text of the email into one or more tokens having one or more tags; enriches one or more tokens in the processed email using data associated with a user of the client device and the one or more tags; and processes the clear text and one or more enriched tokens to generate a data set of one or more feature vectors.

Differential privacy with cloud data

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).

User experience using privatized crowdsourced data

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.

Systems and methods are disclosed for a server learning new words generated by user client devices in a crowdsourced manner while maintaining local differential privacy of client devices. A client device can determine that a word typed on the client device is a new word that is not contained in a dictionary or asset catalog on the client device. New words can be grouped in classifications such as entertainment, health, finance, etc. A differential privacy system on the client device can comprise a privacy budget for each classification of new words. If there is privacy budget available for the classification, then one or more new terms in a classification can be sent to new term learning server, and the privacy budget for the classification reduced. The privacy budget can be periodically replenished.

Learning new words

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.

Modifying a notification on one client device can trigger the generation and transmission of a silent notification to another client device that is associated with the same user account. The silent notification can include instructions to query for and modify a similar notification, if present, on the other client device. Silent notifications that are undeliverable can be stored in offline storage and delivery can be reattempted at a later point in time.

Managing notifications across multiple devices

Systems and methods are disclosed for generating term frequencies of known terms based on crowdsourced differentially private sketches of the known terms. An asset catalog can be updated with new frequency counts for known terms based on the crowdsourced differentially private sketches. Known terms can have a classification. A client device can maintain a privacy budget for each classification of known terms. Classifications can include emojis, deep links, locations, finance terms, and health terms, etc. A privacy budget ensures that a client does not transmit too much information to a term frequency server, thereby compromising the privacy of the client device.

Emoji frequency detection and deep link frequency

Growing community of inventors

San Francisco, CA, United States of America

Andrew H Vyrros