privylayer 0.1.0__tar.gz

privylayer-0.1.0/PKG-INFO

@@ -0,0 +1,187 @@
+Metadata-Version: 2.4
+Name: privylayer
+Version: 0.1.0
+Summary: Privacy layer for AI prompts
+Author: Nithish
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+
+# 🔐 PrivyLayer
+
+> Privacy layer for AI systems — protect sensitive data *before* it reaches AI.
+
+---
+
+## 🚀 Overview
+
+**PrivyLayer** is a lightweight Python library that acts as a **security layer between user input and AI models**.
+
+It detects sensitive information (PII), replaces it with secure placeholders, and restores it after the AI response — ensuring **zero data exposure**.
+
+---
+
+## ⚡ Why PrivyLayer?
+
+Modern AI systems process user input directly, which may include:
+
+* 📱 Phone numbers
+* 📧 Emails
+* 🪪 Aadhaar / PAN
+* 🏦 Bank details
+
+This creates a **privacy risk**.
+
+👉 PrivyLayer solves this by introducing a **reversible masking system**.
+
+---
+
+## 🧠 How It Works
+
+```
+User Input
+   ↓
+PrivyLayer (detect + mask)
+   ↓
+AI Model
+   ↓
+PrivyLayer (restore)
+   ↓
+Final Output
+```
+
+---
+
+## ✨ Features
+
+* 🔍 Detects sensitive data using regex patterns
+* 🔁 Reversible masking (no data loss)
+* 🧠 Smart tokenization system
+* ⚡ Fast and lightweight
+* 🇮🇳 India-specific PII support
+* 🔒 No data stored globally
+
+---
+
+## 📦 Installation
+
+```bash
+pip install privylayer
+```
+
+---
+
+## 🛠️ Usage
+
+### 🔐 Protect (Mask data)
+
+```python
+from privylayer import protect
+
+text = "My phone is 9876543210 and email is test@gmail.com"
+
+mask , context , seen = main.find_p(text)
+
+print(mask)
+```
+
+### Output:
+
+```
+My phone is ⟦PII_PHONE_x1⟧ and email is ⟦PII_EMAIL_x2⟧
+```
+
+---
+
+### 🔓 Restore (Unmask data)
+
+```python
+from privylayer import restore
+
+original = restore(masked, context)
+
+print(original)
+```
+
+### Output:
+
+```
+My phone is 9876543210 and email is test@gmail.com
+```
+
+---
+
+## 🧩 Supported Data Types
+
+* 📱 Phone numbers (India)
+* 📧 Email addresses
+* 🪪 Aadhaar numbers
+* 🧾 PAN numbers
+* 🏦 IFSC codes
+
+---
+
+## 🔐 Token Format
+
+PrivyLayer replaces sensitive data with structured tokens:
+
+```
+⟦PII_TYPE_ID⟧
+```
+
+Example:
+
+```
+⟦PII_PHONE_x1⟧
+⟦PII_EMAIL_x2⟧
+```
+
+---
+
+## ⚠️ Limitations
+
+* Regex-based detection (may not detect names accurately)
+* Does not validate Aadhaar checksum (yet)
+* Context must be preserved for restoration
+
+---
+
+## 🚀 Roadmap
+
+* [ ] AI-based name detection
+* [ ] Risk scoring system
+* [ ] Browser extension
+* [ ] API gateway version
+* [ ] Encryption-based token vault
+
+---
+
+## 🤝 Contributing
+
+Contributions are welcome!
+
+* Fork the repo
+* Create a feature branch
+* Submit a pull request
+
+---
+
+## 📄 License
+
+MIT License
+
+---
+
+## 👨‍💻 Author
+
+Built by Nithish 🚀
+
+---
+
+## 🌟 Vision
+
+> Making AI safe for everyone by protecting sensitive data at the source.
+
+---
+
+⭐ If you like this project, consider giving it a star!

privylayer-0.1.0/README.md

@@ -0,0 +1,178 @@
+# 🔐 PrivyLayer
+
+> Privacy layer for AI systems — protect sensitive data *before* it reaches AI.
+
+---
+
+## 🚀 Overview
+
+**PrivyLayer** is a lightweight Python library that acts as a **security layer between user input and AI models**.
+
+It detects sensitive information (PII), replaces it with secure placeholders, and restores it after the AI response — ensuring **zero data exposure**.
+
+---
+
+## ⚡ Why PrivyLayer?
+
+Modern AI systems process user input directly, which may include:
+
+* 📱 Phone numbers
+* 📧 Emails
+* 🪪 Aadhaar / PAN
+* 🏦 Bank details
+
+This creates a **privacy risk**.
+
+👉 PrivyLayer solves this by introducing a **reversible masking system**.
+
+---
+
+## 🧠 How It Works
+
+```
+User Input
+   ↓
+PrivyLayer (detect + mask)
+   ↓
+AI Model
+   ↓
+PrivyLayer (restore)
+   ↓
+Final Output
+```
+
+---
+
+## ✨ Features
+
+* 🔍 Detects sensitive data using regex patterns
+* 🔁 Reversible masking (no data loss)
+* 🧠 Smart tokenization system
+* ⚡ Fast and lightweight
+* 🇮🇳 India-specific PII support
+* 🔒 No data stored globally
+
+---
+
+## 📦 Installation
+
+```bash
+pip install privylayer
+```
+
+---
+
+## 🛠️ Usage
+
+### 🔐 Protect (Mask data)
+
+```python
+from privylayer import protect
+
+text = "My phone is 9876543210 and email is test@gmail.com"
+
+mask , context , seen = main.find_p(text)
+
+print(mask)
+```
+
+### Output:
+
+```
+My phone is ⟦PII_PHONE_x1⟧ and email is ⟦PII_EMAIL_x2⟧
+```
+
+---
+
+### 🔓 Restore (Unmask data)
+
+```python
+from privylayer import restore
+
+original = restore(masked, context)
+
+print(original)
+```
+
+### Output:
+
+```
+My phone is 9876543210 and email is test@gmail.com
+```
+
+---
+
+## 🧩 Supported Data Types
+
+* 📱 Phone numbers (India)
+* 📧 Email addresses
+* 🪪 Aadhaar numbers
+* 🧾 PAN numbers
+* 🏦 IFSC codes
+
+---
+
+## 🔐 Token Format
+
+PrivyLayer replaces sensitive data with structured tokens:
+
+```
+⟦PII_TYPE_ID⟧
+```
+
+Example:
+
+```
+⟦PII_PHONE_x1⟧
+⟦PII_EMAIL_x2⟧
+```
+
+---
+
+## ⚠️ Limitations
+
+* Regex-based detection (may not detect names accurately)
+* Does not validate Aadhaar checksum (yet)
+* Context must be preserved for restoration
+
+---
+
+## 🚀 Roadmap
+
+* [ ] AI-based name detection
+* [ ] Risk scoring system
+* [ ] Browser extension
+* [ ] API gateway version
+* [ ] Encryption-based token vault
+
+---
+
+## 🤝 Contributing
+
+Contributions are welcome!
+
+* Fork the repo
+* Create a feature branch
+* Submit a pull request
+
+---
+
+## 📄 License
+
+MIT License
+
+---
+
+## 👨‍💻 Author
+
+Built by Nithish 🚀
+
+---
+
+## 🌟 Vision
+
+> Making AI safe for everyone by protecting sensitive data at the source.
+
+---
+
+⭐ If you like this project, consider giving it a star!

privylayer-0.1.0/privylayer/__init__.py

@@ -0,0 +1 @@
+from .core import mask, unmask

privylayer-0.1.0/privylayer/core.py

@@ -0,0 +1,47 @@
+import detect_patterns as dp
+import uuid
+
+uu_id = str(uuid.uuid1())
+
+detect_patterns = {"Phone" : dp.pattern_num , "email": dp.pattern_email , "Aadhaar" : dp.pattern_aadhaar , "PAN" : dp.pattern_pan , "IFSC" : dp.pattern_ifsc}
+
+
+
+
+
+def mask(prompt):
+    
+    context = {}
+    seen = {}
+    counter = 1
+    value = ""
+    masked_txt = prompt
+    for i , k in detect_patterns.items():
+        matches = k.finditer(masked_txt)
+
+        for j in matches:
+            value = j.group()
+
+            if value in seen:
+                token = seen[value]
+
+            else:
+                token_id = f"x_{counter}"
+                token = f"⟦PII_{i}_{token_id}⟧"
+
+                context[token] = value
+                seen[value] = token
+                counter+=1
+            masked_txt = masked_txt.replace(value , token)
+
+
+    return masked_txt , context , seen
+
+def unmask(masked_txt, context):
+    for token, value in context.items():
+        masked_txt = masked_txt.replace(token, value)
+
+    unmask_txt = masked_txt
+
+    return unmask_txt
+

privylayer-0.1.0/privylayer/detect_patterns.py

@@ -0,0 +1,7 @@
+import re
+
+pattern_num = re.compile(r"\b[5-9]\d{9}\b")
+pattern_email = re.compile(r"[a-zA-Z0-9.%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]+")
+pattern_aadhaar = re.compile(r"\b[1-9]\d{11}\b")
+pattern_pan = re.compile(r"\b[A-Z]{5}\d{4}[A-Z]\b")
+pattern_ifsc = re.compile(r"\b[A-Z]{4}0\d{6}\b")

privylayer-0.1.0/privylayer.egg-info/PKG-INFO

@@ -0,0 +1,187 @@
+Metadata-Version: 2.4
+Name: privylayer
+Version: 0.1.0
+Summary: Privacy layer for AI prompts
+Author: Nithish
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+
+# 🔐 PrivyLayer
+
+> Privacy layer for AI systems — protect sensitive data *before* it reaches AI.
+
+---
+
+## 🚀 Overview
+
+**PrivyLayer** is a lightweight Python library that acts as a **security layer between user input and AI models**.
+
+It detects sensitive information (PII), replaces it with secure placeholders, and restores it after the AI response — ensuring **zero data exposure**.
+
+---
+
+## ⚡ Why PrivyLayer?
+
+Modern AI systems process user input directly, which may include:
+
+* 📱 Phone numbers
+* 📧 Emails
+* 🪪 Aadhaar / PAN
+* 🏦 Bank details
+
+This creates a **privacy risk**.
+
+👉 PrivyLayer solves this by introducing a **reversible masking system**.
+
+---
+
+## 🧠 How It Works
+
+```
+User Input
+   ↓
+PrivyLayer (detect + mask)
+   ↓
+AI Model
+   ↓
+PrivyLayer (restore)
+   ↓
+Final Output
+```
+
+---
+
+## ✨ Features
+
+* 🔍 Detects sensitive data using regex patterns
+* 🔁 Reversible masking (no data loss)
+* 🧠 Smart tokenization system
+* ⚡ Fast and lightweight
+* 🇮🇳 India-specific PII support
+* 🔒 No data stored globally
+
+---
+
+## 📦 Installation
+
+```bash
+pip install privylayer
+```
+
+---
+
+## 🛠️ Usage
+
+### 🔐 Protect (Mask data)
+
+```python
+from privylayer import protect
+
+text = "My phone is 9876543210 and email is test@gmail.com"
+
+mask , context , seen = main.find_p(text)
+
+print(mask)
+```
+
+### Output:
+
+```
+My phone is ⟦PII_PHONE_x1⟧ and email is ⟦PII_EMAIL_x2⟧
+```
+
+---
+
+### 🔓 Restore (Unmask data)
+
+```python
+from privylayer import restore
+
+original = restore(masked, context)
+
+print(original)
+```
+
+### Output:
+
+```
+My phone is 9876543210 and email is test@gmail.com
+```
+
+---
+
+## 🧩 Supported Data Types
+
+* 📱 Phone numbers (India)
+* 📧 Email addresses
+* 🪪 Aadhaar numbers
+* 🧾 PAN numbers
+* 🏦 IFSC codes
+
+---
+
+## 🔐 Token Format
+
+PrivyLayer replaces sensitive data with structured tokens:
+
+```
+⟦PII_TYPE_ID⟧
+```
+
+Example:
+
+```
+⟦PII_PHONE_x1⟧
+⟦PII_EMAIL_x2⟧
+```
+
+---
+
+## ⚠️ Limitations
+
+* Regex-based detection (may not detect names accurately)
+* Does not validate Aadhaar checksum (yet)
+* Context must be preserved for restoration
+
+---
+
+## 🚀 Roadmap
+
+* [ ] AI-based name detection
+* [ ] Risk scoring system
+* [ ] Browser extension
+* [ ] API gateway version
+* [ ] Encryption-based token vault
+
+---
+
+## 🤝 Contributing
+
+Contributions are welcome!
+
+* Fork the repo
+* Create a feature branch
+* Submit a pull request
+
+---
+
+## 📄 License
+
+MIT License
+
+---
+
+## 👨‍💻 Author
+
+Built by Nithish 🚀
+
+---
+
+## 🌟 Vision
+
+> Making AI safe for everyone by protecting sensitive data at the source.
+
+---
+
+⭐ If you like this project, consider giving it a star!

privylayer-0.1.0/privylayer.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+README.md
+pyproject.toml
+privylayer/__init__.py
+privylayer/core.py
+privylayer/detect_patterns.py
+privylayer.egg-info/PKG-INFO
+privylayer.egg-info/SOURCES.txt
+privylayer.egg-info/dependency_links.txt
+privylayer.egg-info/top_level.txt

privylayer-0.1.0/privylayer.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

privylayer-0.1.0/privylayer.egg-info/top_level.txt

@@ -0,0 +1 @@
+privylayer

privylayer-0.1.0/pyproject.toml

@@ -0,0 +1,12 @@
+[project]
+name = "privylayer"
+version = "0.1.0"
+description = "Privacy layer for AI prompts"
+authors = [{ name="Nithish" }]
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.8"
+
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"

privylayer-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+