The Statice Platform and SDK got an upgrade: see what's new

With more protection algorithms, advanced PII detection, and new supported data types, protecting your data has never been easier. Take a look at the updated Statice Platform and SDK.

• Five new sanitization operators for structured, semi-structured and unstructured text data.
• PII transformation policies.
• PII detection report.
• Privacy risk mitigation for the synthesization of rare categorical values.

Easily sanitize structured and unstructured data to protect sensitive attributes

We’re bringing new protection operators to the Statice Platform and SDK. You can now replace, hash, mask, redact, or drop Personally Identifiable Information (PII) and Personal Health Information (PHI) in your data in just a few clicks. 

• These ready-to-use operators let you protect sensitive attributes and tailor privacy to your use cases. 
• You can combine operations within a dataset to treat each attribute with the best-suited privacy setting.
• Operators can work with structured data, semi-structured data, or unstructured text data, so you can unlock your sensitive datasets.

Standardize PII protection with the new policy feature

Along with sanitization, we are introducing policies. With these user-made rules, you can specify transformation operators for the attributes of your choice. For example, masking names, redacting customer emails, or hashing zip codes.

‍

Configure policies following the GDPR, HIPAA Safe Harbor, or custom frameworks to ensure compliance. The policies are available across datasets and projects, making standardizing and processing your PII and PHI easy.

Want to learn more about the capabilities of the Statice Platform? Check our product sheet here.

‍

Identify your dataset’s sensitive attributes with the PII detection overview

Get a statistical report to identify all the sensitive attributes detected after the sanitization of your semi-structured and unstructured data. The report is available for any data type in the SDK.

Deal with rare values in a privacy-preserving manner

We improved the detection of rare values in the original data to prevent their synthesization and reduce privacy breach risks.

During the pre-processing phase, privacy safeguards ensure that rare values in a categorical column are not reproduced in the synthetic data. 

‍

You can decide whether to replace rare values with fixed ones (e.g., "N.A.") or with non-rare, randomly selected values from the data. 

‍

Stay up to date & get our product updates directly into your inbox!