content-authenticity

TrustMark - Universal Watermarking for Arbitrary Resolution Images

Python implementation of C2PA: Coalition for Content Provenance and Authenticity.

Pure TypeScript implementation of C2PA manifest reading, validation, and creation

Test what AI watermark and provenance evidence exists, whether it verifies, and what survives publishing.

Sign images and videos with C2PA provenance declaring AI-generated media.

Decision-safe evaluation + Streamlit dashboard for AI vs Human vs Post-Edited AI text detection. Generates a reliability report card (Accuracy, Macro F1, ECE, Brier), calibration plots, confidence histograms, and a coverage-vs-performance abstention curve. Recommends an operating threshold for human-review routing.

Cross-runtime trust surface for LLM-rendered text: Python, Node, and browser runtimes produce byte-identical Ed25519 signatures over JCS-canonical bytes.

The world's first c2pa standard implementation that supports PDF-files signing.

A comprehensive media content authenticity toolkit for verifying audio, video, and imagery through AI, watermarking and metadata analysis.

PHP library for C2PA Content Credentials: build, sign, read & verify manifests, with machine-readable marking of AI-generated content (EU AI Act, Article 50). Framework-agnostic Core + optional Laravel integration.

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)

🕵️ AI content detector and watermark checker. Detect AI-generated text (SynthID, KGW/green-list, Gumbel, Unigram, SWEET) and verify C2PA provenance in images, video, audio, and PDFs. Fast Rust CLI with JSON/XML/YAML output.

AI content authenticity checker — detects AI-generated/manipulated images, videos, and text using Error Level Analysis, EXIF/C2PA provenance forensics, perceptual hashing, and stylometric signals. Every result ships as a transparent, weighted evidence breakdown with confidence scoring, not a black-box verdict. Next.js + browser extension.

ComfyUI custom node for C2PA image signing - digitally sign your images with cryptographic certificates to prove authenticity and provenance

Open-source multimodal AI provenance detection platform with explainable evidence cards, provider consensus, and benchmark-driven quality gates.

🤖 Enterprise multi-agent orchestration platform for autonomous content verification. Built with agentic AI workflows, MCP integration, AgentDB, and advanced deepfake detection. Features agent memory, learning, and collaboration.

Fuck deepfakes. Prove your work. A cryptographic camera app that signs each photo and video as you take it, on the device and offline, so the file carries a record of where it came from that anyone can check.

🌍 Awesome C2PA: Multi-language specifications, tools, and resources for content authenticity

Tiny, dependency-free CLI to detect and inspect C2PA Content Credentials (provenance) in media files — with optional cryptographic validation.

Image provenance for AI agents: the ChronoVerify MCP server. Verify a photo's capture time and provenance (C2PA validation, EXIF/XMP, pixel forensics). Tools: verify_image (typed verdict) and get_signed_report. Local via npx, or hosted at chronoverify.com/mcp/http.