Method and system for detecting sensitive data
AssigneeHuawei Technologies Co., Ltd.
InventorsZhiwei Shang, Zhijun Mo
Life of this patent
Estimating the term…
Abstract
The disclosed systems and methods are directed to detecting sensitive data on a computing device. This includes matching predetermined keywords in input data, to determine data in vicinities of matched keywords in the input data in which sensitive data is likely to be found, and matching predefined patterns associated with sensitive data to the data in vicinities of matched keywords to detect sensitive data. Matching the predetermined keywords occurs prior to matching the predefined patterns, and the data in vicinities of matched keywords is substantially shorter than the input data.
Claims14
An apparatus comprising:
- a processor;
- a memory coupled to the processor;
- and
- a sensitive data detector in the memory and executed by the processor, the sensitive data detector comprising:
- a keyword matcher, executed during a first stage of the sensitive data detector, that matches predetermined keywords in input text, and determines text in vicinities of matched keywords in the input text in which sensitive data is likely to be found, wherein the keyword matcher comprises a pre-constructed automaton configured to match the predetermined keywords in a single pass over the input text;
- and
- a pattern matcher, executed during a second stage of the sensitive data detector, that receives input from the keyword matcher and matches predefined patterns associated with sensitive data to the text in vicinities of matched keywords to detect sensitive data;
- and
- a validator, executed during a third stage of the sensitive data detector, that selects a checksum to apply based on a sensitive data type identified by the pattern matcher and applies the checksum to validate the sensitive data detected by the pattern matcher;
- wherein the keyword matcher executes prior to the pattern matcher;
- and
- wherein the text in vicinities of matched keywords is substantially shorter in length than the input text.
A method of detecting sensitive data on a computing device, the method comprising:
- receiving a set of predetermined keywords;
- generating, based on the set of predetermined keywords, an automaton configured to match the predetermined keywords in a single pass over input data;
- matching, by executing the automaton on the computing device, keywords in the input data, to determine data in vicinities of matched keywords in the input data in which sensitive data is likely to be found;
- matching, on the computing device, predefined patterns associated with sensitive data to the data in vicinities of matched keywords to detect sensitive data;
- and
- selecting, based on a sensitive data type identified for the detected sensitive data, a checksum;
- applying the checksum to the detected sensitive data to validate the detected sensitive data;
- wherein matching the predetermined keywords occurs prior to matching the predefined patterns;
- and
- wherein the data in vicinities of matched keywords is substantially shorter than the input data.
Dependencies are inferred from the claim text.