ML-powered crawling and analysis to identify sensitive data

Deployable across petabyte-scale data storage technologies to identify and contextualize your data at 100,000s of words per second. Combining traditional techniques like regular expressions and dictionaries with machine learning and natural language processing ensures that your sensitive data is identified with a minimum of false positives.

ML classification

Classify sensitive data with out-of-the-box classifiers that will be able to identify data that is sensitive to you at a greater than 93% accuracy rate on day one in most cases. With additional training, the models can achieve better than human accuracy within weeks.

Data remediation

Use casefiles to segregate data into actionable sub-sections work areas for redaction, export, or remediation according to your governance policies.

Unstructured data visibility

Whether an email, a PDF, a powerpoint, or any one of 1000s of other formats, the Data X-Ray will identify files that have sensitive data so that you can triage further actions.

Structured data visibility

Databases are scanned on a column level at speeds that humans simply cannot match. Once sensitive data classes are identified, you can then cross reference this data against other datasources that may use this data.

Dark data identification

Content-level extraction and analysis across files and databases means that you can find dark data that is lurking unseen in your systems and automatically tag that data for remediation or discussion with the data owner.

Data classification

Automated crawling and analysis of your structured and unstructured data at petabyte scale.