User experience using privatized crowdsourced data

• US 10,599,868 B2
• Filed: 11/07/2017
• Issued: 03/24/2020
• Est. Priority Date: 06/04/2017
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Barraclough, Gavin, Dumez, Christophe, Bhowmick, Abhishek, Vyrros, Andrew H., Vaishampayan, Umesh S.
• Primary Examiner(s): Reza, Mohammad W
• Application Number:
  US15/805,632
• Publication Number:
  US 20180349638A1
• Time in Patent Office: 868 Days
• Field of Search: 726 26
• CPC Class Codes: G06F 1/28 Supervision thereof, e.g. detecting power-supply failure by out of limits supervision
• CPC Class Codes: G06F 21/6245 Protecting personal data, e.g. for financial or medical purposes
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/0483 Interaction with page-structured environments, e.g. book metaphor
• CPC Class Codes: H04L 2209/34 Encoding or coding, e.g. Huffman coding or error correction
• CPC Class Codes: H04L 2209/42 Anonymization, e.g. involving pseudonyms
• CPC Class Codes: H04L 63/0428 wherein the data content is protected, e.g. by encrypting or encapsulating the payload
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 9/3239 involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD
• CPC Class Codes: H04W 12/02 Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]

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.

Claims

1. A non-transitory machine-readable medium storing instructions which, when executed by one or more processors of a computing device, cause the computing device to perform operations comprising:

receiving, from a set of client devices, a privatized encoding of a representation of a webpage, wherein each webpage is selected for transmittal in response to exceeding a resource consumption threshold, wherein the privatized encoding comprises a vector including at least one value for the webpage at a position corresponding to a hash value, the hash value is created using a hash function, and the vector is changed at the position corresponding to the created hash value with a predefined probability;

accumulating privatized encodings received from the set of client devices;

estimating a frequency of a selected webpage exceeding the resource consumption threshold, wherein estimating the frequency of the selected webpage includes determining a count based on the accumulated privatized encodings; and

generating a record of the frequency of the selected webpage exceeding the resource consumption threshold based on the estimate of the frequency of the selected webpage.

2. The non-transitory machine-readable medium as in claim 1, wherein the representation of the webpage includes a website associated with the webpage and the operations further comprise estimating a frequency of a website based on the frequency of a selected webpage associated with the website.

3. The non-transitory machine-readable medium as in claim 1, the operations further comprising adjusting the resource consumption threshold based on an analysis of recorded estimated frequencies of one or more webpages.

4. The non-transitory machine-readable medium as in claim 3, wherein the record is a sketch of privatized encodings received from the set of client devices.

5. The non-transitory machine-readable medium as in claim 4, wherein the privatized encodings are differentially privatized encodings.

6. The non-transitory machine-readable medium as in claim 5, wherein estimating the frequency of the selected webpage includes determining the count using a count-mean-sketch operation.

7. The non-transitory machine-readable medium as in claim 1, wherein the resource consumption corresponds to usage of a processor or memory of the computing device.

8. The non-transitory machine-readable medium as in claim 1, wherein the resource consumption corresponds to power usage or data transmission bandwidth.

9. An electronic device comprising:

one or more processors; and

a memory coupled to the one or more processors, the memory storing instructions, which when executed by the one or more processors, cause the electronic device to;

monitor a resource consumption of an application while presenting a webpage from a web site;

determine the resource consumption exceeds a resource consumption threshold;

generate a privatized encoding of a representation of the webpage, wherein to generate the privatized encoding includes to;

create a hash value of the webpage using a hash function,

encode an initialized vector by updating a value of the initialized vector at a position corresponding to the created hash value, and

change at least some of the values of the vector with a predefined probability; and

transmit the privatized encoding of the representation of the webpage to a server, wherein the server is to accumulate a sketch of privatized encodings from different devices to estimate a count of the webpages exceeding the resource consumption threshold amongst the different devices.

10. The electronic device as in claim 9, wherein the server is to estimate a frequency a website has a webpage exceeding the resource consumption.

11. The electronic device as in claim 9, wherein the resource consumption corresponds to usage of the one or more processors or the memory coupled to the one or more processors.

12. The electronic device as in claim 9, wherein the resource consumption corresponds to power usage of the electronic device or data transmission bandwidth consumption of the electronic device.

13. The electronic device as in claim 9, wherein the application accessing the webpage includes a browser.

14. The electronic device as in claim 13, wherein to monitor the resource consumption of the application accessing the webpage includes monitoring the resource consumption of a process id of a tab of the application corresponding to the webpage.

15. The electronic device as in claim 9, wherein to generate the privatized encoding of the representation of the webpage includes to:

create the hash value of the webpage using a randomly selected hash function, and

encode the initialized vector via a sign flip of the value of the vector at the position corresponding to the created hash value.

16. The electronic device as in claim 15, wherein the predefined probability is based on a pre-determined privacy parameter.

17. A data processing system comprising:

one or more processors; and

a memory coupled to the one or more processors, the memory storing instructions which, when executed by the processor, cause the processor to perform operations comprising;

receiving, from each of a set of client devices, a privatized encoding of a representation of a webpage, wherein each webpage is selected for transmittal in response to exceeding a resource consumption threshold wherein the privatized encoding comprises a vector including at least one value for the webpage at a position corresponding to a hash value, the hash value is created using a hash function, and the vector is changed at the position corresponding to the created hash value with a predefined probability;

accumulating a sketch of the privatized encodings received from the set of client devices;

estimating a count of a selected webpage amongst the webpages included in the sketch; and

generating a record of the count of the selected webpage exceeding the resource consumption threshold based on the estimate of the count of the selected webpage.

18. The data processing system as in claim 17, wherein the representation of the webpage includes a website associated with the webpage and the operations further comprise estimating a frequency of a website based on the count of webpages included in the sketch that are associated with the website.

19. The data processing system as in claim 17, the operations further comprising adjusting the resource consumption threshold based on an analysis of estimated counts of one or more webpages included with the sketch.

20. The data processing system as in claim 17, wherein the resource consumption corresponds to usage of one or more processors or of memory coupled to the one or more processors.

21. The data processing system as in claim 17, wherein the resource consumption corresponds to power usage or data transmission bandwidth.