Python implementation of C2PA: Coalition for Content Provenance and Authenticity.
-
Updated
Jun 22, 2022 - Python
Python implementation of C2PA: Coalition for Content Provenance and Authenticity.
Pure TypeScript implementation of C2PA manifest reading, validation, and creation
The AI native file format — trust scores, provenance, and compliance metadata that embed into every file your AI touches. pip install akf
An ethical dataset supporting research in digital content provenance and authenticity, compliant with C2PA standards. Licensed for non-commercial use under CC BY-NC 4.0.
Local-first Unicode steganography detector, encrypted text watermark studio, and robust blind image watermark toolkit.
An innovative concept to safeguard visual media against generative AI. This repository is the main hub for the 'Adaptive Spider Web' project, detailing its layered defense, dynamic noise structure, and the verification app concept
Cryptographic Proof of Effort (CPoE) — IETF Internet-Draft specification for verifiable attestation of human cognitive involvement in digital content creation, built on the RATS architecture (RFC 9334)
Combat fake news with cryptographic image verification. Origin Lens analyzes C2PA Content Credentials and EXIF metadata to detect AI-generated content, verify digital signatures, and reveal complete edit history. Privacy-first open source iOS app with on-device verification. (arXiv:2602.03423)
MCP server for reading C2PA content provenance manifests from media files (Google Lyria AI MP3s, Adobe Content Credentials, etc.)
Sebuah konsep inovatif untuk menjaga media visual dari penyalahgunaan AI generatif. Repositori ini adalah hub utama untuk proyek 'Adaptive Spider Web', yang merinci pertahanan berlapis, struktur noise dinamis, dan konsep aplikasi verifikasinya
An invisible watermark is still a signal. A lightweight CNN ensemble that detects SynthID — the imperceptible watermark in ChatGPT / GPT-Image-2 images — trained on a laptop and validated against the official verifier.
The AI Provenance Protocol (APP) is an open standard for verifying AI-generated content. It provides a machine-readable format to track model identity, inputs, and human review. Designed for EU AI Act compliance (Article 50) and global governance, APP ensures transparency and accountability for any AI output.
CPP (Capture Provenance Profile) - Open specification for cryptographic proof of media capture events. Features RFC 6962 Merkle trees for deletion detection, RFC 3161 timestamping, and optional ACE (Attested Capture Extension) for zero-knowledge biometric attestation. Part of the VAP Framework.
Sign your web content with a hardware-backed OIS identity. Verify offline.
One-command EU AI Act Article 50 disclosure (visible label + C2PA credential + watermark) for face-swap, voice-clone, and lip-sync outputs.
Structured author identity that travels with the work — across feeds, search, the fediverse, and AI — from one source of truth in WordPress.
The open specification for the Technical Evidence Package (TEP) format, the Authorship Evidence Constitution, and the LucidGrid Tool Registry.
Add a description, image, and links to the content-provenance topic page so that developers can more easily learn about it.
To associate your repository with the content-provenance topic, visit your repo's landing page and select "manage topics."