--- title: "PII & PHI Redaction Guides and Best Practices" description: "Practical guides on PII and PHI redaction: self-hosted pipelines, LLM and RAG privacy, HIPAA and GDPR, and de-identification, from the Philter maintainers." url: "https://philterd.ai/blog/" --- Blog # PII & PHI Redaction Guides and Best Practices Practical guides on PII and PHI redaction: self-hosted pipelines, LLM and RAG privacy, HIPAA and GDPR, and de-identification, from the Philter maintainers. ## Start here - June 7, 2026 ### [How to Redact PII Before Sending to an LLM: Chat, RAG, and AI Agents](https://philterd.ai/blog/redact-pii-before-sending-to-an-llm/) Redact PII and PHI before any prompt reaches an LLM, keeping data on your own infrastructure. A self-hosted pipeline for chat, RAG, and AI agents. - June 18, 2026 ### [How to Deploy Philter in 5 Minutes on the AWS Marketplace](https://philterd.ai/blog/deploy-philter-in-5-minutes-aws-marketplace/) Subscribe, launch into your own VPC, and redact PII in minutes. A step-by-step guide to deploying the self-hosted Philter API from the AWS Marketplace. - August 8, 2026 ### [Redact PDFs Offline on Windows so No Data Leaves Your PC](https://philterd.ai/blog/redact-pdfs-offline-on-windows/) Philter Desktop redacts PDFs entirely on your Windows PC, including scanned pages read with on-device OCR. No uploads, no server, and it works offline. ## Latest posts - October 29, 2026 [Phield](https://philterd.ai/categories/phield/) · [Monitoring](https://philterd.ai/categories/monitoring/) ### [Introducing Phield: Monitoring How PII Actually Moves Through Your Systems](https://philterd.ai/blog/introducing-phield-pii-drift-monitoring/) Phield is a PII drift and trend monitor. It takes PII type counts over an API or Kafka, builds a baseline, and alerts via PagerDuty or Slack on deviations. - [Phield](https://philterd.ai/tags/phield/) - [Monitoring](https://philterd.ai/tags/monitoring/) - [Drift-Detection](https://philterd.ai/tags/drift-detection/) - [Announcement](https://philterd.ai/tags/announcement/) - October 26, 2026 [Philter](https://philterd.ai/categories/philter/) · [Redaction](https://philterd.ai/categories/redaction/) ### [Announcing Philter 4, the Most Capable Philter Yet](https://philterd.ai/blog/announcing-philter-4/) Philter 4 is out. It is API-only, stores data in SQLite or MongoDB, adds a tamper-evident redaction ledger, and tightens security defaults. See what changed. - [Release](https://philterd.ai/tags/release/) - [Philter](https://philterd.ai/tags/philter/) - October 8, 2026 [Philter Desktop](https://philterd.ai/categories/philter-desktop/) · [Redaction](https://philterd.ai/categories/redaction/) ### [Philter Desktop 1.2.0 Adds ITIN and SIN Detection and Keep-Last-4 Redaction](https://philterd.ai/blog/philter-desktop-1-2-0-itin-sin-and-new-redaction-strategies/) Philter Desktop 1.2.0 detects ITINs and Canadian SINs and adds strategies like keeping the last 4 digits of a card number, masking, hashing, and encryption. - [Philter-Desktop](https://philterd.ai/tags/philter-desktop/) - [Windows](https://philterd.ai/tags/windows/) - [Release](https://philterd.ai/tags/release/) - [Itin](https://philterd.ai/tags/itin/) - [Sin](https://philterd.ai/tags/sin/) - [Filter-Strategies](https://philterd.ai/tags/filter-strategies/) - October 6, 2026 [Philter](https://philterd.ai/categories/philter/) ### [Philterd Joins the gBETA Fall 2026 Cohort at Marshall's iCenter](https://philterd.ai/blog/philterd-joins-gbeta-marshall-fall-2026-cohort/) Philterd is one of five West Virginia companies in the gBETA at Marshall's iCenter Fall 2026 cohort, a free seven-week accelerator run with gener8tor. - [Announcement](https://philterd.ai/tags/announcement/) - [Gbeta](https://philterd.ai/tags/gbeta/) - [West-Virginia](https://philterd.ai/tags/west-virginia/) - October 1, 2026 [Redaction](https://philterd.ai/categories/redaction/) · [Compliance](https://philterd.ai/categories/compliance/) ### [Show Me the Code Path: Why Open Source Wins the PII Redaction Audit](https://philterd.ai/blog/show-me-the-code-path-open-source-pii-redaction-audit/) When an auditor asks how a redaction decision was made, open source lets you answer with the code path. A decisive edge for government and healthcare buyers. - [Open Source](https://philterd.ai/tags/open-source/) - [Audit](https://philterd.ai/tags/audit/) - [Government](https://philterd.ai/tags/government/) - [Compliance](https://philterd.ai/tags/compliance/) - September 10, 2026 [Philter](https://philterd.ai/categories/philter/) · [Redaction](https://philterd.ai/categories/redaction/) ### [Redaction Policies as Code: Building and Sharing Policies with the Philterd Policy Library](https://philterd.ai/blog/redaction-policies-as-code/) A redaction policy decides what leaves your building. Treating it as a versioned, tested file rather than a console setting is what makes it reviewable. - [Policies](https://philterd.ai/tags/policies/) - [Open Source](https://philterd.ai/tags/open-source/) - [Compliance](https://philterd.ai/tags/compliance/) - September 3, 2026 [Integrations](https://philterd.ai/categories/integrations/) · [Philter](https://philterd.ai/categories/philter/) ### [Redacting PII and PHI from Audio Transcriptions with Philter and Amazon Transcribe](https://philterd.ai/blog/redacting-audio-transcriptions-with-philter-and-amazon-transcribe/) A hands-on guide to redacting PII and PHI from audio transcripts. Run Philter against an Amazon Transcribe transcript and deploy two AWS architectures at scale. - [Amazon-Transcribe](https://philterd.ai/tags/amazon-transcribe/) - [Audio](https://philterd.ai/tags/audio/) - [Integration](https://philterd.ai/tags/integration/) - [Aws](https://philterd.ai/tags/aws/) - [PHI](https://philterd.ai/tags/phi/) - August 20, 2026 [Philter](https://philterd.ai/categories/philter/) · [Redaction](https://philterd.ai/categories/redaction/) ### [Integrating Philter AI Proxy with OpenAI and Anthropic in Production](https://philterd.ai/blog/philter-ai-proxy-openai-anthropic-production/) Pointing a client at the proxy is one line. Where it sits relative to your AI gateway, and what it does with streaming responses, are the parts to get right. - [Ai-Proxy](https://philterd.ai/tags/ai-proxy/) - [LLM](https://philterd.ai/tags/llm/) - [Deployment](https://philterd.ai/tags/deployment/) - August 13, 2026 [Philter](https://philterd.ai/categories/philter/) · [Redaction](https://philterd.ai/categories/redaction/) ### [Air-Gapped PII Redaction for Government: A Deployment Walkthrough](https://philterd.ai/blog/air-gapped-redaction-deployment-walkthrough/) A walkthrough for standing up Philter 3.4.2 and PhEye in a disconnected enclave: pinned images, offline transfer, and proving there is no egress. - [Air-Gapped](https://philterd.ai/tags/air-gapped/) - [Government](https://philterd.ai/tags/government/) - [Deployment](https://philterd.ai/tags/deployment/) ## Earlier posts - ### 2026 - [Five Ways a Healthcare App Leaks PHI Without Anyone Noticing](https://philterd.ai/blog/five-ways-a-healthcare-app-leaks-phi/) Aug 10, 2026 - [Redact PDFs Offline on Windows so No Data Leaves Your PC](https://philterd.ai/blog/redact-pdfs-offline-on-windows/) Aug 8, 2026 - [The Clean Room for AI Training Data: Redact, Review, Measure](https://philterd.ai/blog/the-clean-room-for-ai-training-data-redact-review-measure/) Aug 6, 2026 - [When a PDF Is Too Dense to Redact](https://philterd.ai/blog/when-a-pdf-is-too-dense-to-redact/) Aug 3, 2026 - [Moving PII Redaction Off the CPU: An FPGA Experiment](https://philterd.ai/blog/moving-pii-redaction-off-the-cpu-an-fpga-experiment/) Jul 31, 2026 - [Why Your LLM Provider's Built-In Guardrails Are Not Enough](https://philterd.ai/blog/why-llm-provider-guardrails-are-not-enough/) Jul 30, 2026 - [Redact Both Sides of the LLM: Inputs and Outputs](https://philterd.ai/blog/redact-both-sides-of-the-llm-inputs-and-outputs/) Jul 30, 2026 - [Can an LLM Leak Its Training Data, and Why You Cannot Un-Train PII](https://philterd.ai/blog/can-an-llm-leak-its-training-data-why-you-cannot-un-train-pii/) Jul 23, 2026 - [Designing a HIPAA Architecture on AWS](https://philterd.ai/blog/designing-a-hipaa-architecture-on-aws/) Jul 16, 2026 - [Introducing Philter Router: The Right Policy for Every File](https://philterd.ai/blog/introducing-philter-router-the-right-policy-for-every-file/) Jul 10, 2026 - [Introducing Philter Desktop: Redact Documents Right on Your Windows PC](https://philterd.ai/blog/introducing-philter-desktop-redact-documents-on-your-windows-pc/) Jul 9, 2026 - [PII Redaction Is a Lifecycle, Not a One-Time Fix](https://philterd.ai/blog/pii-redaction-is-a-lifecycle-not-a-one-time-fix/) Jul 8, 2026 - [Our Project Issues Are Now Public](https://philterd.ai/blog/issues-now-in-public-repositories/) Jul 7, 2026 - [The Phileas Trino Connector Is Now Open Source](https://philterd.ai/blog/phileas-trino-connector-now-open-source/) Jun 25, 2026 - [How to Tell if a PII Redaction Model Is Any Good](https://philterd.ai/blog/how-to-tell-if-a-pii-redaction-model-is-any-good/) Jun 24, 2026 - [Precision, Recall, or F1: Which Redaction Metric Matters Most in Your Industry](https://philterd.ai/blog/precision-recall-f1-redaction-metric-by-industry/) Jun 19, 2026 - [Redact PII From Your AI Agent in One Block of Config](https://philterd.ai/blog/philter-mcp-pii-redaction-for-ai-agents/) Jun 18, 2026 - [How to Deploy Philter in 5 Minutes on the AWS Marketplace](https://philterd.ai/blog/deploy-philter-in-5-minutes-aws-marketplace/) Jun 18, 2026 - [How We Built PhEye's PII Name Models](https://philterd.ai/blog/building-the-ph-eye-pii-name-models/) Jun 17, 2026 - [How We Use Philter Scope to Evaluate Our PII Models](https://philterd.ai/blog/auditing-our-pii-models-with-philter-scope/) Jun 17, 2026 - [Multilingual Medical PII Redaction: English and French with Philter](https://philterd.ai/blog/multilingual-medical-pii-redaction-english-french-philter/) Jun 16, 2026 - [Cutting False Positives on National IDs with Checksum Validation](https://philterd.ai/blog/checksum-validation-national-id-redaction/) Jun 15, 2026 - [philter-sdk-java 2.0.0: Built for Philter 4.0.0](https://philterd.ai/blog/philter-sdk-java-2-0-0/) Jun 12, 2026 - [Phileas 4.0.0](https://philterd.ai/blog/phileas-4-0-0/) Jun 10, 2026 - [How to Redact PII Before Sending to an LLM: Chat, RAG, and AI Agents](https://philterd.ai/blog/redact-pii-before-sending-to-an-llm/) Jun 7, 2026 - [Introducing PhiSQL: The Query Language for PII Operations](https://philterd.ai/blog/introducing-phisql-the-query-language-for-pii-operations/) May 28, 2026 - [PhEye Update: Unified Branch, GPU Support, and Streamlined Testing](https://philterd.ai/blog/pheye-unified-branch-gpu-support-and-streamlined-testing/) May 26, 2026 - [Introducing Arbiter: Human-in-the-Loop PII Redaction](https://philterd.ai/blog/introducing-arbiter-human-in-the-loop-pii-redaction/) May 16, 2026 - [The TCO of "Free" Cloud PII Redaction: AWS Comprehend, Google DLP, vs Self-Hosted at Scale](https://philterd.ai/blog/tco-cloud-pii-redaction-aws-comprehend-google-dlp-vs-self-hosted/) May 14, 2026 - [PII Masking and Redaction in Trino with the Phileas Connector](https://philterd.ai/blog/the-phileas-trino-connector-redaction-as-sql/) May 3, 2026 - [Redaction for Legal and E-Discovery: Privilege, Rule 9037, and the In-House Counsel's Pipeline](https://philterd.ai/blog/redaction-for-legal-and-e-discovery-privilege-rule-9037-counsel-pipeline/) Apr 30, 2026 - [The Ethics of Training: Why We Use Synthetic Data](https://philterd.ai/blog/the-ethics-of-training-why-we-use-synthetic-data/) Apr 19, 2026 - [Building a HIPAA-Compliant Medical Chatbot](https://philterd.ai/blog/building-a-hipaa-compliant-medical-chatbot/) Apr 14, 2026 - [Building a Privacy-Aware RAG System](https://philterd.ai/blog/building-a-privacy-aware-rag-system/) Apr 8, 2026 - [Redaction for Financial Services: PCI DSS, GLBA, and the Real-World Data Pipeline](https://philterd.ai/blog/redaction-for-financial-services-pci-dss-glba-real-world-pipelines/) Mar 25, 2026 - [Architecting Privacy in Kafka: Real-Time Redaction for Streaming Data](https://philterd.ai/blog/architecting-privacy-in-kafka-real-time-redaction-for-streaming-data/) Mar 11, 2026 - [Beyond Regex: Why General LLMs Fail at PII Discovery](https://philterd.ai/blog/beyond-regex-why-general-llms-fail-at-pii-discovery/) Mar 4, 2026 - [Compliance as Code: Integrating Philter into Your CI/CD Pipeline](https://philterd.ai/blog/compliance-as-code-integrating-philter-into-your-ci-cd-pipeline/) Feb 25, 2026 - [Migrating from AWS Comprehend to Philter: A Practical Transition Guide](https://philterd.ai/blog/migrating-from-aws-comprehend-to-philter/) Feb 18, 2026 - [Redaction for Insurance: Claims, Customer Data, and the State-by-State Patchwork](https://philterd.ai/blog/redaction-for-insurance-claims-and-customer-data-glba-and-state-rules/) Feb 12, 2026 - [Open Source vs. Black Box: Why You Can't Afford "Trust Me" Privacy](https://philterd.ai/blog/open-source-vs-black-box-trust-me-privacy/) Feb 5, 2026 - [Automating HIPAA Safe Harbor: A Blueprint for Healthcare Data Pipelines](https://philterd.ai/blog/automating-hipaa-safe-harbor-a-blueprint-for-healthcare-data-pipelines/) Jan 25, 2026 - [Privacy Shouldn't Be a Guessing Game: Evaluating Redaction with Philter Scope](https://philterd.ai/blog/evaluating-redaction-with-philter-scope/) Jan 18, 2026 - [Why API-Based Redaction is a Security Antipattern](https://philterd.ai/blog/why-api-based-redaction-is-a-security-antipattern/) Jan 17, 2026 - [Redaction for Government and Federal Workloads: FedRAMP, CMMC, ITAR, and the Air-Gap Imperative](https://philterd.ai/blog/redaction-for-government-and-federal-fedramp-cmmc-itar/) Jan 9, 2026 - ### 2025 - [Deploying Philter in Air-Gapped Environments](https://philterd.ai/blog/deploying-philter-in-air-gapped-environments/) Dec 27, 2025 - [From Phileas to Philter: The Evolution of Our Open Source Engine](https://philterd.ai/blog/from-phileas-to-philter-the-evolution-of-our-open-source-engine/) Dec 19, 2025 - [Redaction for Education: FERPA, Student Records, and Research Data Pipelines](https://philterd.ai/blog/redaction-for-education-ferpa-student-records-and-research-data/) Dec 14, 2025 - [Snowflake PII Redaction: A Practical Integration Guide](https://philterd.ai/blog/snowflake-pii-redaction-a-practical-integration-guide/) Dec 6, 2025 - [Redacting PII and PHI in OpenSearch Data Prepper Pipelines](https://philterd.ai/blog/redacting-pii-and-phi-in-opensearch-data-prepper-pipelines/) Nov 18, 2025 - [Philter 3.1.0](https://philterd.ai/blog/philter-3-1-0/) Mar 23, 2025 - [Phileas 2.12.0](https://philterd.ai/blog/phileas-2-12-0/) Mar 20, 2025 - [Why Using an LLM to Redact PII and PHI is a Bad Idea](https://philterd.ai/blog/why-using-an-llm-to-identify-and-redact-pii-and-phi-is-a-bad-idea/) Feb 17, 2025 - [Shielding Your Search: Redacting PII and PHI in Elasticsearch with the Search Redact Plugin](https://philterd.ai/blog/shielding-your-search-redacting-pii-and-phi-in-elasticsearch-with-search-redact/) Jan 11, 2025 - [Shielding Your Search: Redacting PII and PHI in OpenSearch with the Search Redact Plugin](https://philterd.ai/blog/shielding-your-search-redacting-pii-and-phi-in-opensearch-with-search-redact/) Jan 10, 2025 - [Phileas 2.10.0](https://philterd.ai/blog/phileas-2-10-0/) Jan 6, 2025 - ### 2024 - [Phileas in Graylog – Removing PII from Logs](https://philterd.ai/blog/phileas-in-graylog-removing-pii-from-logs/) Dec 1, 2024 - [Phileas 2.9.1](https://philterd.ai/blog/phileas-2-9-1/) Nov 27, 2024 - [Automatically Redacting PII and PHI from Files in Amazon S3 using Amazon Macie and Philter](https://philterd.ai/blog/automatically-redacting-pii-and-phi-from-files-in-amazon-s3-using-amazon-macie-and-philter/) Nov 17, 2024 - [Philter as an AI Policy Layer](https://philterd.ai/blog/philter-as-an-ai-policy-layer/) Oct 10, 2024 - ### 2023 - [Phileas: The Open Source PII and PHI redaction engine](https://philterd.ai/blog/phileas-the-open-source-pii-and-phi-redaction-engine/) May 22, 2023 Browse every post by [category](https://philterd.ai/categories/) or by [tag](https://philterd.ai/tags/).