The Hidden Difficulties of Redacting PDF Documents
PDFs leak redacted text in ways most people don't anticipate — invisible text layers, embedded files, attached portfolios, metadata, the works. A deep dive into why PDF redaction is harder than it looks, with famous failures and Philter's approach.
Prompt Engineering for Privacy: Practical Patterns for Not Leaking PII
Every prompt sent to an LLM is a data egress point. Six concrete patterns for structuring prompts, redacting inputs, and scanning outputs so PII doesn't leak through the model.
Building a Privacy-Aware RAG System
RAG pipelines have two distinct PII leak vectors: ingestion and inference. A defense-in-depth blueprint with code, using Philter, Philter AI Proxy, and the rest of the Philterd toolkit.
Why API-Based Redaction is a Security Antipattern
Sending sensitive data to a third-party redaction API creates the security holes you're trying to close. Here's why true data sovereignty requires a self-hosted engine — and how Philter delivers it.
Deploying Philter in Air-Gapped Environments
How to deploy Philter — and the rest of the Philterd toolkit — into completely offline VPCs and disconnected cloud regions. No phone-home, no hidden telemetry, no external dependencies.