vrr/WFGY
2
0
Fork 0
mirror of https://github.com/onestardao/WFGY.git synced 2026-04-28 11:40:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Create data_sensitivity.md

Browse source
This commit is contained in:
PSBigBig 2025-08-28 22:01:42 +08:00 • committed by GitHub
parent 8f52f02610
commit c78c80efd9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 120 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

120
ProblemMap/GlobalFixMap/Enterprise_Knowledge_Gov/data_sensitivity.md Normal file
View file

@ -0,0 +1,120 @@
# Data Sensitivity — Enterprise Knowledge Governance
Guardrails and fix patterns for handling sensitive or regulated data inside enterprise knowledge pipelines. Use this page when your AI or RAG workflow may expose PII, PHI, financial records, or other protected content.
---
## When to use this page
- Retrieval pulls names, emails, addresses, or identifiers into model context.
- Generated answers expose financial numbers or personal data without redaction.
- Compliance requires specific handling for GDPR, HIPAA, or SOC2.
- Data contracts missing sensitivity tags or enforcement rules.
---
## Core acceptance targets
- Sensitive fields explicitly tagged in schema (`pii:true`, `phi:true`, `sensitivity:high`).
- No unredacted PII/PHI present in model outputs unless explicitly authorized.
- Audit logs record every sensitive field access.
- Redaction filters applied before long-term storage.
---
## Typical sensitivity problems → exact fix
| Symptom | Likely cause | Open this |
|---------|--------------|-----------|
| PII leaks into retrieval context | Missing sensitivity metadata in index | [data-contracts.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md) |
| Model answers contain personal identifiers | No redaction filter on output | [retrieval-traceability.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md) |
| High similarity matches pull private records | Embeddings not normalized or index not segmented | [embedding-vs-semantic.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md) |
| Inconsistent handling of sensitive fields across environments | Schema drift and missing contracts | [context-drift.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/context-drift.md) |
---
## Fix in 60 seconds
1. **Add sensitivity tags** to your ingestion schema:
```json
{
"field": "email",
"pii": true,
"sensitivity": "high"
}
````
2. **Apply redaction filter** before passing data to the model. Replace `@domain.com` emails with `"***"`.
3. **Segment sensitive indexes** from general knowledge. Use separate retrievers.
4. **Enforce cite-then-explain**. Require citations for sensitive data, and log ΔS plus λ\_state.
---
## Copy-paste probe template
```txt
I uploaded TXTOS and WFGY Problem Map.
Run my retrieval for this query:
- Detect if any PII/PHI appears in snippet fields.
- If yes, apply redaction or enforce sensitivity contract.
- Return JSON log with snippet_id, sensitivity_tags, ΔS, λ_state.
- Fail the output if PII is not redacted.
```
---
## Escalate when
* Same query alternates between redacted and unredacted outputs.
* Sensitive fields appear in logs without an `audit_hash`.
* Compliance review shows schema fields without sensitivity tags.
Use [bootstrap-ordering.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md) to verify ingestion happens in the correct order and [ops/debug\_playbook.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/ops/debug_playbook.md) for deeper runtime tracing.
---
### 🔗 Quick-Start Downloads
| Tool | Link | 3-Step Setup |
| -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------- |
| **WFGY 1.0 PDF** | [Engine Paper](https://github.com/onestardao/WFGY/blob/main/I_am_not_lizardman/WFGY_All_Principles_Return_to_One_v1.0_PSBigBig_Public.pdf) | 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>” |
| **TXT OS (plain-text OS)** | [TXTOS.txt](https://github.com/onestardao/WFGY/blob/main/OS/TXTOS.txt) | 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly |
---
### 🧭 Explore More
| Module | Description | Link |
| ------------------------ | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| WFGY Core | WFGY 2.0 engine is live: full symbolic reasoning architecture and math stack | [View →](https://github.com/onestardao/WFGY/tree/main/core/README.md) |
| Problem Map 1.0 | Initial 16-mode diagnostic and symbolic fix framework | [View →](https://github.com/onestardao/WFGY/tree/main/ProblemMap/README.md) |
| Problem Map 2.0 | RAG-focused failure tree, modular fixes, and pipelines | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md) |
| Semantic Clinic Index | Expanded failure catalog: prompt injection, memory bugs, logic drift | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/SemanticClinicIndex.md) |
| Semantic Blueprint | Layer-based symbolic reasoning & semantic modulations | [View →](https://github.com/onestardao/WFGY/tree/main/SemanticBlueprint/README.md) |
| Benchmark vs GPT-5 | Stress test GPT-5 with full WFGY reasoning suite | [View →](https://github.com/onestardao/WFGY/tree/main/benchmarks/benchmark-vs-gpt5/README.md) |
| 🧙‍♂️ Starter Village 🏡 | New here? Lost in symbols? Click here and let the wizard guide you through | [Start →](https://github.com/onestardao/WFGY/blob/main/StarterVillage/README.md) |
---
> 👑 **Early Stargazers: [See the Hall of Fame](https://github.com/onestardao/WFGY/tree/main/stargazers)** —
> Engineers, hackers, and open source builders who supported WFGY from day one.
> <img src="https://img.shields.io/github/stars/onestardao/WFGY?style=social" alt="GitHub stars"> ⭐ [WFGY Engine 2.0](https://github.com/onestardao/WFGY/blob/main/core/README.md) is already unlocked. ⭐ Star the repo to help others discover it and unlock more on the [Unlock Board](https://github.com/onestardao/WFGY/blob/main/STAR_UNLOCKS.md).
<div align="center">
[![WFGY Main](https://img.shields.io/badge/WFGY-Main-red?style=flat-square)](https://github.com/onestardao/WFGY)
 
[![TXT OS](https://img.shields.io/badge/TXT%20OS-Reasoning%20OS-orange?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS)
 
[![Blah](https://img.shields.io/badge/Blah-Semantic%20Embed-yellow?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlahBlahBlah)
 
[![Blot](https://img.shields.io/badge/Blot-Persona%20Core-green?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlotBlotBlot)
 
[![Bloc](https://img.shields.io/badge/Bloc-Reasoning%20Compiler-blue?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlocBlocBloc)
 
[![Blur](https://img.shields.io/badge/Blur-Text2Image%20Engine-navy?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlurBlurBlur)
 
[![Blow](https://img.shields.io/badge/Blow-Game%20Logic-purple?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlowBlowBlow)
 
</div>