MITIGATING USE OF MACHINE SOLVABLE HIPS

• US 20120189194A1
• Filed: 01/26/2011
• Published: 07/26/2012
• Est. Priority Date: 01/26/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Srivastava, Kumar S.
• Granted Patent: US 8,885,931 B2
• Time in Patent Office: Days
• US Class Current: 382/161
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06F 21/36 by graphic or iconic representation

Abstract

One or more techniques and/or systems are disclosed for mitigating machine solvable human interactive proofs (HIPs). A classifier is trained over a set of one or more training HIPs that have known characteristics for OCR solvability and HIP solving pattern from actual use. A HIP classification is determined for a HIP (such as from a HIP library used by a HIP generator) using the trained classifier. If the HIP is classified by the trained classifier as a merely human solvable classification, such that it may not be solved by a machine, the HIP can be identified for use in the HIP generation system. Otherwise, the HIP can be altered to (attempt to) be merely human solvable.

Claims

1. A computer-based method for mitigating machine solvable human interactive proofs (HIPs), comprising:

determining a HIP classification for a HIP using a trained classifier, utilizing a computer-based processor, where the classifier is trained over a set of one or more training HIPs having known characteristics for;

HIP optical character recognition (OCR) solvability; and

HIP solving pattern; and

identifying the HIP for use in a HIP generation system if the HIP classification comprises a merely human solvable classification.

2. The method of claim 1, comprising subjecting the HIP to OCR using one or more OCR engines to determine OCR solvability for the HIP.

3. The method of claim 1, comprising collecting HIP solving pattern data from a HIP use log.

4. The method of claim 3, collecting HIP solving pattern data comprising collecting data indicating one or more of:

mistakes made when using a HIP;

time duration for entering the HIP;

time duration for entering respective characters in the HIP; and

characteristics of how the respective characters are entered for the HIP.

5. The method of claim 1, comprising training the classifier over a set of one or more training HIPs using characteristics of HIPs solved by humans, and characteristics of HIPs solved by machines.

6. The method of claim 1, the characteristics comprising an Internet-based address reputation for a location of where the HIP was solved.

7. The method of claim 6, comprising collecting an Internet-based address for the HIP from a HIP use log.

8. The method of claim 1, comprising classifying the HIP as one of the following:

machine solvable;

human solvable;

both human and machine solvable; and

neither human nor machine solvable.

9. The method of claim 8, classifying the HIP comprising classifying the HIP using a desired threshold for a classification confidence score for respective classifications.

10. The method of claim 8, if the HIP comprises a machine solvable HIP, comprising removing the HIP from use in the HIP generation system.

11. The method of claim 8, if the HIP comprises a both human and machine solvable HIP, comprising:

identifying one or more machine solvable parts of the HIP; and

modifying the identified one or more machine solvable parts into a human solvable part to generate a modified HIP.

12. The method of claim 8, comprising:

determining a HIP classification for a modified HIP using the trained classifier, where the modified HIP comprises a both human and machine solvable HIP that is modified to be comprise a merely human solvable HIP; and

using the modified HIP in a HIP generation system if the HIP classification is the merely human solvable classification.

13. The method of claim 1, comprising one or more of:

running one or more HIPs in an existing HIP store for the HIP generation system through the trained classifier; and

running respective new HIPs through the trained classifier prior to use by the HIP generation system.

14. A system for mitigating machine solvable human interactive proofs (HIPs), comprising:

a computer-based processor configured to process data for the system;

an optical character recognition (OCR) component, operably coupled with the processor, configured to determine OCR solvability for a HIP;

a HIP solving pattern component, operably coupled with the processor, configured to identify one or more HIP solving patterns for the HIP; and

a HIP classification component, operably coupled with the OCR component and the HIP solving pattern component, configured to determine a HIP classification for the HIP using the OCR solvability and one or more HIP solving patterns for the HIP, where the HIP classification comprises one or more of;

machine solvable; and

human solvable.

15. The system of claim 14, comprising a HIP store component configured to utilize merely the HIPs that are classified as human solvable.

16. The system of claim 14, comprising a HIP modification component configured to modify a HIP that is at least partially machine solvable into a merely human solvable HIP.

17. The system of claim 16, the HIP modification component comprising a HIP portion identification component configured to identify one or more portions of the at least partially machine solvable HIP that are machine solvable.

18. The method of claim 16, the HIP modification component comprising a HIP image modifier component configured to alter the at least partially machine solvable portion of the HIP to a merely human solvable portion of the HIP.

19. The system of claim 14, comprising a HIP log data collection component configured to identify one or more of the following from a HIP log:

mistakes made when using a HIP;

time duration for entering the HIP;

time duration for entering respective characters in the HIP;

characteristics of how the respective characters are entered for the HIP; and

Internet-based address reputation for a location of where the HIP was solved.

20. A computer-based method for mitigating machine solvable human interactive proofs (HIPs), comprising:

subjecting a HIP to OCR using one or more OCR engines to determine OCR solvability for the HIP;

collecting HIP solving pattern data from a HIP use log, comprising collecting data indicating one or more of;

mistakes made when using a HIP;

time duration for entering the HIP;

time duration for entering respective characters in the HIP; and

characteristics of how the respective characters are entered for the HIP;

training a classifier over a set of one or more training HIPs using characteristics of HIPs solved by humans, and characteristics of HIPs solved by machines, where a set of one or more training HIPs have known characteristics for at least one of;

HIP optical characteristic recognition (OCR) solvability;

HIP solving pattern; and

an Internet-based address reputation for a location of where the HIP was solved;

determining a HIP classification for the HIP using the trained classifier, utilizing a computer-based processor; and

identifying the HIP for use in a HIP generation system if the HIP classification comprises a merely human solvable classification.