Reducing Photo-Tagging Spam

• US 20170034094A1
• Filed: 10/17/2016
• Published: 02/02/2017
• Est. Priority Date: 05/02/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Fung, Felix
• Granted Patent: US 10,432,562 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: H04L 51/212 using filtering or selective blocking
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

A photo spam detector detects illegitimate non-natively captured images through extracting image features and feeding the extracted features into a probabilistic model. The probabilistic model categorizes the photo as legitimate or illegitimate. Requests to tag one or more users in a photo are analyzed by a tag analyzer that assesses relationships between the tag requests themselves, social relationships between the tagged users, and the presence or absence of faces within the regions specified by the tag requests. Based on the classification of images or tags as illegitimate, a social networking system applies one or more social media distribution policies to the image or tags to suppress or prohibit distribution.

Claims

1. A method comprising, by one or more computing systems:

receiving a plurality of requests to tag a plurality of respective users in an image;

processing the plurality of requests to determine a relationship between two or more of the requests;

determining a probability that the two or more requests are illegitimate tags based on the determined relationship;

comparing the determined probability to a predetermined threshold to determine that the determined probability is greater than the predetermined threshold; and

applying one or more distribution policies to the two or more requests based on the determined probability being greater than the predetermined threshold.

2. The method of claim 1, wherein determining the relationship between the two or more requests comprises determining a relationship between respective names of two or more users associated respectively with the two or more requests.

3. The method of claim 2, wherein determining the relationship between the respective names of the two or more users comprises determining that the two or more requests have been received in alphabetical order, the alphabetical order being determined based on the respective names of the two or more users associates with the two or more requests.

4. The method of claim 1, further comprising accessing social-relationship information associated with two or more users associated with the two or more requests, wherein the determined relationship between the two or more requests comprises one or more social relationships between the two or more users associated with the two or more requests, the one or more social relationships being determined based on the accessed social-relationship information.

5. The method of claim 4, further comprising:

determining coefficient scores for the two or more users associated with the two or more requests based on the one or more social relationships; and

adjusting the probability that the two or more requests are illegitimate tags based on the coefficient scores.

6. The method of claim 4, wherein the social-relationship information comprises interaction information between any of the two or more users associated with the two or more requests.

7. The method of claim 4, wherein the social-relationship information comprises identification of first-degree contacts for each of the two or more users associated with the two or more requests.

8. The method of claim 1, wherein determining the relationship between the two or more requests comprises monitoring a temporal rate at which the two or more requests are received.

9. The method of claim 1, wherein the one or more distribution policies comprise reducing a rate at which actions may be performed on the image.

10. The method of claim 1, wherein the one or more distribution policies comprise prohibiting actions on the image.

11. The method of claim 1, wherein the one or more distribution policies comprise suppressing distribution of the image.

12. The method of claim 1, wherein the one or more distribution policies comprise suppressing distribution of actions on the image.

13. A system comprising:

one or more processors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to;

receive a plurality of requests to tag a plurality of respective users in an image;

process the plurality of requests to determine a relationship between two or more of the requests;

determine a probability that the two or more requests are illegitimate tags based on the determined relationship;

compare the determined probability to a predetermined threshold to determine that the determined probability is greater than the predetermined threshold; and

apply one or more distribution policies to the two or more requests based on the determined probability being greater than the predetermined threshold.

14. The system of claim 13, wherein determining the relationship between the two or more requests comprises determining a relationship between respective names of two or more users associated respectively with the two or more requests.

15. The system of claim 14, wherein determining the relationship between the respective names of the two or more users comprises determining that the two or more requests have been received in alphabetical order, the alphabetical order being determined based on the respective names of the two or more users associates with the two or more requests.

16. The system of claim 13, wherein determining the relationship between the two or more requests comprises monitoring a temporal rate at which the two or more requests are received.

17. One or more computer-readable non-transitory storage media embodying software that is operable when executed by a computing device to:

receive a plurality of requests to tag a plurality of respective users in an image;

process the plurality of requests to determine a relationship between two or more of the requests;

determine a probability that the two or more requests are illegitimate tags based on the determined relationship;

compare the determined probability to a predetermined threshold to determine that the determined probability is greater than the predetermined threshold; and

apply one or more distribution policies to the two or more requests based on the determined probability being greater than the predetermined threshold.

18. The media of claim 17, wherein determining the relationship between the two or more requests comprises determining a relationship between respective names of two or more users associated respectively with the two or more requests.

19. The media of claim 18, wherein determining the relationship between the respective names of the two or more users comprises determining that the two or more requests have been received in alphabetical order, the alphabetical order being determined based on the respective names of the two or more users associates with the two or more requests.

20. The media of claim 19, wherein determining the relationship between the two or more requests comprises monitoring a temporal rate at which the two or more requests are received.