Protection of private data

1. A method performed under control of a server, comprising:

calculating co-occurrence probabilities of a plurality of combinations, each of which includes at least two elements that are included in original message data;

extracting, from the original message data, a first data set that includes at least one combination that has a first co-occurrence probability from among the plurality of combinations and a second data set that includes at least one combination that has a second co-occurrence probability from among the plurality of combinations;

generating first dummy data by using the first data set and second dummy data by using the second data set, the first dummy data reduces the first co-occurrence probability of the first data set and the second dummy data increases the second co-occurrence probability of the second data set;

adding the generated first dummy data and second dummy data to the original message data to generate obfuscated message data;

rendering the obfuscated message data to a web browser that is installed on an end device; and

transmitting, to the end device, a program file that makes the first dummy data and second dummy data invisible from the obfuscated message rendered on the web browser,

wherein the first co-occurrence probability is ranked in from top 10 percent to top 20 percent of the co-occurrence probabilities, and

wherein the second co-occurrence probability is ranked in from top 40 percent to top 60 percent of the co-occurrence probabilities.

2. The method of claim 1 , wherein the generating the second dummy data includes:

a combination from among the at least one combination included in the second data set.

3. The method of claim 2 , wherein the generating of the first dummy data includes:

selecting, from the original message data, a dummy combination that includes one of the at least two elements included in the at least one combination included in the first data set, and

wherein the dummy combination is not included in the first data set.

4. The method of claim 3 , wherein the first dummy data includes a dummy message, and

wherein the generating of the first dummy data further includes:

generating the dummy message that includes at least two elements included in the dummy combination by using a text generating template.

5. The method of claim 1 , wherein the at least two elements includes words in a message and at least one of time information in which the message is generated, or location information at which the message is generated.

6. A server, comprising:

a processor; and

a non-transitory memory coupled to the processor, wherein the non-transitory memory stores program instructions executable by the processor to cause the system to perform operations comprising:

calculating co-occurrence probabilities of a plurality of combinations, each of which includes at least two elements that are included in original message data;

extracting, from the original message data, a first data set that includes at least one combination that has a first co-occurrence probability from among the plurality of combinations and a second data set that includes at least one combination that has a second co-occurrence probability from among the plurality of combinations;

generating first dummy data by using the first data set and second the second data set by using the first data set, the first dummy data reduces the first co-occurrence probability of the first data set and the second dummy data increases the second co-occurrence probability of the second data set; and

adding the generated first dummy data and second dummy data to the original message data to generate obfuscated message data,

wherein the first co-occurrence probability is ranked in from top 10 percent to top 20 percent of the co-occurrence probabilities, and

wherein the second co-occurrence probability is ranked in from top 40 percent to top 60 percent of the co-occurrence probabilities.

7. The server of claim 6 wherein the operations further comprise:

rendering the obfuscated message data to a web browser that is installed on an end device.

8. The server of claim 7 , wherein the operations further comprise:

generating a program file that makes the dummy data invisible from the obfuscated message rendered on the web browser, and

transmitting further transmits, to the end device, the program file.

9. The server of claim 6 , wherein generating the second dummy data comprises:

generating a second dummy data that includes a combination from among the at least one combination included in the second data set.

10. The server of claim 9 , wherein generating the first dummy data comprises generating the first dummy data by selecting, from the original message data, a dummy combination that includes one of the at least two elements included in the least one combination included in the first data set, and

wherein the dummy combination is not included in the first data set.

11. The server of claim 10 , wherein the dummy data includes a dummy message, and

wherein generating the first dummy data comprises generating a dummy message that includes at least two elements included in the dummy combination by using a text generating template.

12. The server of claim 6 , wherein the at least two elements includes one or more words in a message and at least one of time information in which the message is generated, or location information at which the message is generated.

13. The server of claim 6 , further comprising:

a first database configured to store the original message data; and

a second database configured to store the first data set and the second data set.

14. A non-transitory computer-readable storage medium having stored thereon computer-executable instructions that, in response to execution, cause a server to perform operations, comprising:

calculating co-occurrence probabilities of a plurality of combinations, each of which includes at least two elements that are included in original message data;

extracting, from the original message data, a first data set that includes at least one combination that has a first co-occurrence probability from among the plurality of combinations and a second data set that includes at least one combination that has a second co-occurrence probability from among the plurality of combinations;

generating first dummy data by using the first data set and second dummy data by using the second data set, the first dummy data reduces the first co-occurrence probability of the first data set and the second dummy data increases the second co-occurrence probability of the second data set; and

adding the generated first dummy data and second dummy data to the original message data to generate obfuscated message data,

wherein the first co-occurrence probability is ranked in from top 10 percent to top 20 percent of the co-occurrence probabilities, and

wherein the second co-occurrence probability is ranked in from top 40 percent to top 60 percent of the co-occurrence probabilities.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the generating of the dummy data includes

generating a second dummy data that includes a combination from among the at least one combination included in the second data set.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the generating of the first dummy data includes:

selecting, from the original message data, a dummy combination that includes one of the at least two elements included in the least one combination included in the first data set, and

wherein the dummy combination is not included in the first data set.

17. The non-transitory computer readable storage medium of claim 16 , wherein the dummy data includes a dummy message, and

wherein the generating of the first dummy data further includes generating the dummy message that includes at least two elements included in the dummy combination by using a text generating template.

18. The non-transitory computer readable storage medium of claim 14 , wherein the generating the second dummy data includes a combination from among the at least one combination included in the second data set.