Arnaud Legendre

US Patent:

20190068628, Feb 28, 2019

Filed:

Oct 12, 2018

Appl. No.:

16/159481

Inventors:

- Cupertino CA, US
Andrew H. Vyrros - San Francisco CA, US
Umesh S. Vaishampayan - Santa Clara CA, US
Gaurav Kapoor - Santa Clara CA, US
Julien Freudiger - San Francisco CA, US
Vipul Ved Prakash - San Francisco CA, US
Arnaud Legendre - San Francisco CA, US
Steven Duplinsky - San Francisco CA, US

International Classification:

H04L 29/06
G06F 21/62
G06F 17/27
G06N 99/00
G06F 17/22

Abstract:

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.

US Patent:

20170359363, Dec 14, 2017

Filed:

Jun 19, 2017

Appl. No.:

15/627269

Inventors:

- Cupertino CA, US
Andrew H. Vyrros - San Francisco CA, US
Umesh S. Vaishampayan - Santa Clara CA, US
Gaurav Kapoor - Santa Clara CA, US
Julien Freudinger - Mountain View CA, US
Vipul Ved Prakash - San Francisco CA, US
Arnaud Legendre - San Francisco CA, US
Steven Duplinsky - San Francisco CA, US

International Classification:

H04L 29/06
G06N 99/00

Abstract:

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.

US Patent:

20170359364, Dec 14, 2017

Filed:

Jun 30, 2017

Appl. No.:

15/640266

Inventors:

- Cupertino CA, US
Andrew H. Vyrros - San Francisco CA, US
Umesh S. Vaishampayan - Santa Clara CA, US
Gaurav Kapoor - Santa Clara CA, US
Julien Freudinger - Mountain View CA, US
Vipul Ved Prakash - San Francisco CA, US
Arnaud Legendre - San Francisco CA, US
Steven Duplinsky - San Francisco CA, US

International Classification:

H04L 29/06
G06N 99/00

Abstract:

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.