apple_generative_model_safety_decrypted  by BlueFalconHD

Decrypted Apple Intelligence safety filters

Created 2 months ago
296 stars

Top 89.6% on SourcePulse

GitHubView on GitHub
Project Summary

This repository provides decrypted safety filter files for Apple Intelligence's generative models, enabling researchers and power users to examine the mechanisms behind content moderation. It offers tools to extract, decrypt, and consolidate these filters, facilitating analysis of Apple's approach to AI safety.

How It Works

The project leverages Python scripts to decrypt proprietary safety override files used by Apple's generative models. It requires obtaining an encryption key by attaching Xcode's LLDB debugger to a specific Apple system process (GenerativeExperiencesSafetyInferenceProvider). Once the key is acquired, a Python script decrypts the asset files, which are then processed by another script to combine and deduplicate metadata into human-readable JSON formats, categorized by region and locale.

Quick Start & Requirements

  • Install cryptography via pip: pip install cryptography
  • Requires Xcode's LLDB debugger and access to macOS system files.
  • Decryption process involves attaching LLDB to /System/Library/ExtensionKit/Extensions/GenerativeExperiencesSafetyInferenceProvider.appex/Contents/MacOS/GenerativeExperiencesSafetyInferenceProvider.
  • Decrypted overrides are available as of June 28, 2025.
  • Further details on the decryption process are in HOW.md.

Highlighted Details

  • Provides decrypted JSON files containing explicit reject, remove, and regexReject rules for generative model outputs.
  • Includes scripts to extract encryption keys using LLDB and decrypt the safety overrides.
  • Offers functionality to combine and deduplicate metadata across different regions and locales.
  • Analyzes safety filters for models like com.apple.gm.safety_deny.output.code_intelligence.base.

Maintenance & Community

No specific community channels, contributors, or roadmap are mentioned in the README.

Licensing & Compatibility

The repository does not explicitly state a license. The presence of Apple's proprietary system files suggests potential legal and compatibility issues for redistribution or commercial use.

Limitations & Caveats

The process requires specific Apple hardware and software (Xcode LLDB), and relies on internal system file paths that may change with OS updates. The licensing status of the decrypted files is unclear, posing a risk for any use beyond personal analysis.

Health Check
Last Commit

3 weeks ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
1
Star History
10 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.