Identify direct identifiers (such as PII and PHI) automatically with our AI-powered PII Scanner
Book a demo
Automatically detect and manage personally identifiable information (PII) in your data using Syntho’s AI-powered PII Scanner
Leverage our AI-powered PII scanner to automatically detect columns and instances in your database containing direct identifiers, such as Personally Identifiable Information (PII) and Protected Health Information (PHI).
Once columns containing PII are recognized, our platform facilitates de-identification methods such as deletion, substitution with mock data, or synthesis, fortifying database privacy.
Efficiently identify PII automatically with AI
Enhanced data privacy
The AI-powered PII Scanner ensures enhanced data privacy by automatically identifying and flagging personally identifiable information (PII) within datasets.
Compliance with regulations
By swiftly and accurately identifying PII elements, the AI-powered scanner helps organizations adhere to regulatory requirements such as GDPR, HIPAA, and CCPA.
Time and cost savings
Automating the process of PII detection significantly reduces the time and resources required for manual data inspection, enabling organizations to achieve compliance more efficiently and cost-effectively.
One can easily configure the PII Scanner via our user interface via the “PII” tab. This feature has two scan options:
All columns that are identified as PII are shown in the list of PII entities on the PII tab and are labeled PII on the column header on the Job Settings tab.
Next to the automatic identification of PII, our platform also automatically suggests the correct mocker for each PII entity, saving time and effort for the user. By using this feature, users can ensure that the sensitive original PII is protected and is replaced by representative mock data with preserved referential integrity for multi-table databases via our consistent mapping functionality.
Yes, users can also identify PII entities manually as an alternative to the PII scanner. Users can also apply mockers manually as an alternative to the automated suggested mockers. However, we optimized our platform in such a way that AI does the work for you to mitigate manual work and to be able to process large data volumes fast.
Explore the Syntho user documentation
Utilize the PII Text Scanner to perform an in-depth analysis of your data, detecting any personally identifiable information (PII) present within fields containing free text.
Use our Synthetic Mock Data techniques to replace PII with mockers.
The Syntho Engine allows users to remove identified PII. When PII is removed, it will simply be deleted from the data or replaced by a default value, such as “*” or “PII”. This allows organizations to protect information.
Example: Original text with identified PII:
“ John Smith applied for a loan of $10,000 with our bank on 03/01/2023 . He provided his social security number 123-45-6789 , date of birth 01/01/1985 , and employment information Syntho . Our loan officer conducted a credit check and verified his information. Based on his credit score and employment history, he was approved for the loan and the funds were deposited into his account on 03/03/2023 .”
The Syntho Engine allows users to replace identified PII with the entity. An entity is a placeholder that replaces specific identifying information to protect an individual’s privacy.
When PII is replaced with entities, sensitive information such as names or dates are replaced with placeholders such as “<name>” or “<date>”. This allows organizations to maintain the structure of their data, while protecting the sensitive information contained within it.
Text with PII replaced by entities:
“ <Name> applied for a loan of <Amount> with our bank on <date> . They provided their social security number <SSN> , date of birth <DOB> , and employment information <Employer> . Our loan officer conducted a credit check and verified their information. Based on their credit score and employment history, they were approved for the loan and the funds were deposited into their account on <date> .”
Similarly, the Syntho Engine allows users to replace identified PII with a mocker. A mocker is a fictitious value that is used to replace specific identifying information. Mocker values are not real and have no relation to the original data, but they maintain the same format as the original data to preserve its usability.
When PII is replaced with mockers, sensitive information is replaced with fictitious data. In this case, sensitive information such as names or dates are replaced with mock names such as “Wim Kees” or mock dates such as “03-05-2023”. This allows organizations to maintain the structure of their and have a representative mock value as alternative, while protecting the sensitive information contained within it.
Text with PII replaced by mockers:
“ Jake Brown applied for a loan of $23,340 with our bank on 12/11/2023 . They provided their social security number 987-65-4321 , date of birth 04/02/1989 , and employment information XYZ Company . Our loan officer conducted a credit check and verified their information. Based on their credit score and employment history, they were approved for the loan and the funds were deposited into their account on 13/12/2023 .”
Text with PII replaced by the default value “PII”:
“ PII applied for a loan of PII with our bank on PII . They provided their social security number PII , date of birth PII , and employment information PII . Our loan officer conducted a credit check and verified their information. Based on their credit score and employment history, they were approved for the loan and the funds were deposited into their account on PII .”
Explore other features that we provide
Test Data Management
Data Masking
Mimic (sensitive) data with AI to generate synthetic data twins
PII, PHI, and other direct identifiers are sensitive and can be spotted manually or automatically with our PII scanner to save time and minimize manual work. Then, one can apply Mockers to substitute real values with mock values to de-identify data and enhance privacy.
PII stands for Personal Identifiable Information. PHI stands for Personal Health Information and is an extended version of PII dedicated to health information. Both PII and PHI are identifiers and relate to any information that can be used to distinguish or trace an individual’s identity directly. Here, with identifiers, only one person shares this trait.
Test data management (TDM) is the process of creating, maintaining, and controlling the data used for non-production environments (test, development and acceptance environments).
De-identification is a process used to protect sensitive information by removing or modifying personally identifiable information (PII) from a dataset or database.
Unlock data access, accelerate development, and enhance data privacy.
Keep up to date with synthetic data news
