Systems and methods for identifying privacy leakage information
The disclosed computer-implemented method for identifying privacy leakage information may include (1) identifying, at the computing device, at least one informative word in a digital text and (2) performing a security action that identifies privacy leakage information, where the security action includes (A) determining, for at least one identified informative word, a type of privacy leakage and a respective confidence score indicating a probability the identified informative word causes the type of privacy leakage, (B) determining, using the respective confidence score, a combined confidence score for each respective element within a level of detail to display, and (C) displaying, on a display device, the combined confidence score for each respective element within the level of detail to display. Various other methods, systems, and computer-readable media are also disclosed.
1. A computer-implemented method for identifying privacy leakage information, at least a portion of the method being performed by a computing device comprising at least one processor, the method comprising:
identifying, at the computing device, at least one informative word in a digital text; and
performing a security action that identifies privacy leakage information, wherein the security action comprises:
determining, for at least one identified informative word, a type of privacy leakage and a respective confidence score indicating a probability the identified informative word causes the type of privacy leakage;
determining, using the respective confidence score, a combined confidence score for each respective element within a level of detail to display; and
displaying, on a display device, the combined confidence score for each respective element within the level of detail to display.
2. The computer-implemented method of claim 1 , further comprising receiving, from a graphical user interface, an input indicating the level of detail to display.
3. The computer-implemented method of claim 1 , wherein the digital text is in a set of electronic documents.
4. The computer-implemented method of claim 1 , wherein the level of detail to display is in a hierarchy of detail comprising:
a document level of detail;
a sentence level of detail; and
a word level of detail.
5. The computer-implemented method of claim 1 , wherein the level of detail to display is a document level of detail and each respective element is a document.
6. The computer-implemented method of claim 1 , wherein the level of detail to display is a sentence level of detail and each respective element is a sentence.
7. The computer-implemented method of claim 1 , wherein the level of detail to display is a word level of detail and each respective element is a word.
8. The computer-implemented method of claim 1 , wherein the determining the combined confidence score for each respective element further comprises:
adding respective confidence scores for each type of privacy leakage for each identified informative word in the respective element;
normalizing the sum of respective confidence scores; and
sorting the normalized sum.
9. The computer-implemented method of claim 1 , wherein the displaying further comprises determining a two-way tree-structured index comprising:
the combined confidence score for each respective element within each of the levels of detail; and
associations between related elements across different levels of detail.
10. The computer-implemented method of claim 9 , wherein the displaying further comprises identifying the combined confidence score to display by:
receiving an input indicating a requested level of detail to display;
retrieving, based on the received input, the combined confidence score from the two-way tree-structured index; and
displaying, on the display device, the retrieved combined confidence score.
11. The computer-implemented method of claim 1 , wherein the displaying further comprises determining a two-way tree-structured index comprising:
a first list of types of privacy leakage, ranked by respective confidence scores, for each respective element within each of the levels of detail;
respective confidence scores for each type of privacy leakage in the first list;
a second list of subtypes of privacy leakage, ranked by respective confidence scores, for each respective type of privacy leakage in the second list;
respective confidence scores for each subtype of privacy leakage in the first list;
the respective elements within each of the levels of detail; and
associations between related elements across different levels of detail.
12. The computer-implemented method of claim 11 , wherein the displaying further comprises identifying per-element privacy leakage detail to display by:
receiving an input indicating a requested level of per-element privacy leakage detail to display;
retrieving, from the two-way tree-structured index and based on the received input, per-element privacy leakage detail and respective confidence scores from at least one of the first list and the second list within the requested level of detail to display; and
displaying, on the display device, the retrieved per-element privacy leakage detail and the respective confidence scores.
13. The computer-implemented method of claim 1 , wherein the security action further comprises replacing the at least one informative word in the digital text with at least one replacement word.
14. A system for identifying privacy leakage information, the system comprising:
at least one physical processor; and
physical memory comprising computer-executable instructions that, when executed by the physical processor, cause the physical processor to:
identify, at the system, at least one informative word in a digital text; and
perform a security action that identifies privacy leakage information, wherein the security action comprises:
determining, for at least one identified informative word, a type of privacy leakage and a respective confidence score indicating a probability the identified informative word causes the type of privacy leakage;
determining, using the respective confidence score, a combined confidence score for each respective element within a level of detail to display; and
displaying, on a display device, the combined confidence score for each respective element within the level of detail to display.
15. The system of claim 14 , further computer-executable instructions that, when executed by the physical processor, cause the physical processor to receive, from a graphical user interface, an input indicating the level of detail to display.
16. The system of claim 14 , wherein the displaying further comprises determining a two-way tree-structured index comprising:
the combined confidence score for each respective element within each of the levels of detail; and
associations between related elements across different levels of detail.
17. The system of claim 16 , wherein the displaying further comprises identifying the combined confidence score to display by:
receiving an input indicating a requested level of detail to display;
retrieving, based on the received input, the combined confidence score from the two-way tree-structured index; and
displaying, on the display device, the retrieved combined confidence score.
18. A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the computing device to:
identify, at the computing device, at least one informative word in a digital text; and
perform a security action that identifies privacy leakage information, wherein the security action comprises:
determining, for at least one identified informative word, a type of privacy leakage and a respective confidence score indicating a probability the identified informative word causes the type of privacy leakage;
determining, using the respective confidence score, a combined confidence score for each respective element within a level of detail to display; and
displaying, on a display device, the combined confidence score for each respective element within the level of detail to display.
19. The non-transitory computer-readable medium of claim 18 , further comprising one or more computer-executable instructions that, when executed by at least one processor of the computing device, cause the computing device to receive, from a graphical user interface, an input indicating the level of detail to display.
20. The non-transitory computer-readable medium of claim 18 , wherein the displaying further comprises determining a two-way tree-structured index comprising:
the combined confidence score for each respective element within each of the levels of detail; and
associations between related elements across different levels of detail.