WEBSITE ACCESS CONTROL

• US 20160205109A1
• Filed: 01/13/2015
• Published: 07/14/2016
• Est. Priority Date: 01/13/2015
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Khoo, Li Quan, Kohli, Pushmeet, Bachrach, Yoram, Radlinski, Filip, Paquet, Ulrich
• Granted Patent: US 10,154,041 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06F 21/6218 to a system of files or objects, e.g. local or distributed file system or database
• CPC Class Codes: G06F 21/6254 by anonymising data, e.g. decorrelating personal data from the owner's identification
• CPC Class Codes: G06F 2221/2137 Time limited access, e.g. to a computer or data
• CPC Class Codes: G06F 2221/2149 Restricted operating environment
• CPC Class Codes: H04L 63/101 Access control lists [ACL]
• CPC Class Codes: H04L 63/102 Entity profiles

Abstract

A method of controlling access to content such as web sites on the intranet or interne is described. For example, the method comprises receiving an address of content to be accessed and obtaining similarity of the address to previously labeled addresses of other content items. The similarity is based on co-occurrence of addresses of content items in records of browsing sessions from many consenting users. For example, a browsing session record comprises addresses of content items accessed by a user in a time period during which the user is actively accessing content. A co-occurrence of addresses of content items is the existence of the addresses in the same browsing session record. Access to the content is then controlled on the basis of the similarity.

Claims

1. A website filter comprising:

an input configured to receive an address of content to be accessed;

a processor configured to obtain similarity of the address to previously labeled addresses of other content items, where the similarity is based on co-occurrence of addresses of content items in records of browsing sessions from many consenting users, a browsing session record comprising addresses of content items accessed by a given user in a time period during which the given user is actively accessing content, a co-occurrence of addresses of content items being the existence of the addresses in the same browsing session record; and

an output configured to control access to the content to be accessed on the basis of the similarity.

2. The website filter of claim 1 wherein the input is configured to receive the address of the content to be accessed together with an identifier of an end user device requesting access to the content;

and wherein the previously labeled addresses of other content items comprise addresses labeled by a user associated with the end user device.

3. The website filter of claim 1 wherein the processor is arranged to obtain the similarity from an entity which repeatedly accesses the record of browsing sessions such that changes in the record of browsing sessions over time are taken into account.

4. The website filter of claim 1 wherein the processor is configured to take into account changes in the previously labeled addresses over time.

5. The website filter of claim 1 wherein the processor is configured to obtain the similarity from an entity which computes the similarity between addresses A and B, at least in part, as the number of times addresses A and B occur in the same browsing session divided by the total number of times addresses A and B occur in any of the sessions.

6. The website filter of claim 1 wherein the processor is configured to obtain the similarity from an entity which computes the similarity between addresses by calculating a multi-dimensional feature vector of each address and computing similarities between pairs of the feature vectors.

7. The website filter of claim 1 wherein the processor is configured to obtain the similarity from an entity which computes the similarity using clustering or a kernel based distance function.

8. The website filter of claim 1 comprising a memory storing the previously labeled addresses, and wherein the processor is configured to generate a graphical user interface requesting a label for one or more content addresses.

9. The website filter of claim 1 wherein the previously labeled addresses of other content items comprise at least one content item labeled as to be blocked.

10. The website filter of claim 1 wherein the processor is configure to generate a graphical user interface displaying addresses of content and similarity of the addresses to the previously labeled addresses computed by the processor.

11. The website filter of claim 1 integral with an operating system of an end user device such that the input is configured to intercept requests for content generated for output from the end user device and such that the operating system is configured to control access to the content on the basis of the similarity.

12. The website filter of claim 1 wherein the processor is configured to compute the similarity and wherein the processor is configured to pre-process the browsing records by any of:

selecting frequent addresses, merging similar addresses, filtering by geographic origin of sessions.

13. A computer-implemented method of controlling access to content comprising:

receiving an address of content to be accessed;

obtaining similarity of the address to previously labeled addresses of other content items, where the similarity is based on co-occurrence of addresses of content items in records of browsing sessions from many consenting users, a browsing session record comprising addresses of content items accessed by a user in a time period during which the user is actively accessing content, a co-occurrence of addresses of content items being the existence of the addresses in the same browsing session record; and

controlling access to the content to be accessed on the basis of the similarity by any of;

allowing access to the content, blocking access to the content, triggering an alert.

14. The method of claim 13 comprising receiving the address of the content to be accessed together with an identifier of an end user device requesting access to the content;

and wherein the previously labeled addresses of other content items comprise addresses labeled by a user associated with the end user device.

15. The method of claim 13 comprising obtaining the similarity from an entity which repeatedly accesses the record of browsing sessions such that changes in the record of browsing sessions over time are taken into account.

16. The method of claim 13 wherein obtaining the similarity comprises any of:

computing the similarity, requesting the similarity from another entity.

17. A computer-readable media with device-executable instructions that, when executed by a computing-based device, direct the computing-based device to perform steps comprising:

receiving an address of content to be accessed;

obtaining similarity of the address to previously labeled addresses of other content items, where the similarity is based on co-occurrence of addresses of content items in records of browsing sessions from many consenting users, a browsing session record comprising addresses of content items accessed by a user in a time period during which the user is actively accessing content, a co-occurrence of addresses of content items being the existence of the addresses in the same browsing session record; and

controlling access to the content to be accessed on the basis of the similarity by any of;

allowing access to the content, blocking access to the content, triggering an alert.

18. The computer-readable media of claim 17 with device-executable instructions that, when executed by a computing-based device, direct the computing-based device to perform steps comprising receiving the address of the content to be accessed together with an identifier of an end user device requesting access to the content;

and wherein the previously labeled addresses of other content items comprise addresses labeled by a user associated with the end user device.

19. The computer-readable media of claim 17 with device-executable instructions that, when executed by a computing-based device, direct the computing-based device to perform steps comprising computing the similarity between addresses A and B at least as the number of times addresses A and B occur in the same browsing session divided by the total number of times addresses A and B occur in any of the sessions.

20. The computer-readable media of claim 17 with device-executable instructions that, when executed by a computing-based device, direct the computing-based device to perform steps comprising:

computing the similarity between addresses by calculating a multi-dimensional feature vector of each address and computing similarities between pairs of the feature vectors.