PDF Redaction

PDF Redaction provides AI-powered redaction capabilities for individuals and organizations, aiming to identify and permanently remove personal data from PDFs. It operates in various deployment modes, including cloud, on-premise, and desktop, with data staying controlled by users according to the chosen setup. The product emphasizes security and data control across its offerings, from browser-based tools to self-hosted solutions.

PDF Redaction offers detection for personal, financial, and health data, plus custom rules to handle identifiers specific to an organization. It supports review workflows and batch processing, with the option to run in air-gapped environments. The platform integrates with automation tools and provides a developer-focused API and SDKs to embed redaction capabilities into other systems.

The team behind PDF Redaction highlights their experience in ML, NLP, and OCR, and notes that the product runs on an open-source foundation with libraries like ScaleDP and Spark-based processing. The product suite includes a web editor, a Studio for collaboration, and desktop and API variants, all built to keep data within the user’s infrastructure when required.

The product presents a range of deployment options and licenses, including cloud APIs, on-premise Studio, and desktop apps, with a focus on compliance workflows such as GDPR, HIPAA, and CCPA. It provides professional services and customization options to tailor redaction rules and pipelines to organizational needs.

Use cases

• Occasional document redaction in a browser