C2PA
Definition
Coalition for Content Provenance and Authenticity. A cross-industry group that has published an open technical specification for embedding cryptographically signed provenance manifests in media files. A verified C2PA manifest establishes who created or edited a file and with what tools, providing a forward-looking chain of authenticity from capture.
- Full name
- Coalition for Content Provenance and Authenticity
- Field
- Media forensics and digital provenance
- Mechanism
- Cryptographically signed provenance manifest
- Records
- Creator, editing tools, and edit history
Common questions
What does a C2PA manifest actually prove in a forensic context?+
A verified manifest establishes a documented chain of custody for a media file from the point it was signed, showing who or what tool created or edited it and when, which is strongest when capture devices sign content at the moment of creation rather than only at export.
What happens to C2PA provenance if a file is stripped of its metadata?+
Removing or failing to preserve the manifest breaks the chain, so an image circulating without C2PA data cannot be confirmed as inauthentic on that basis alone, it simply lacks the forward-looking provenance record the standard is designed to provide.
Is C2PA a detection tool for existing fake images?+
No, it is a provenance and authentication standard applied at creation and editing time, distinct from after-the-fact detection methods such as forensic artifact analysis that try to identify manipulation in content that was never signed.
Related terms
- Content Credentials
- Adobe's brand name for C2PA-compliant provenance manifests. A Content Credentials badge on an image indicates that a signed, auditable creation history is...
- Daubert Standard
- The US federal evidentiary standard (Daubert v. Merrell Dow Pharmaceuticals, 1993) requiring that expert testimony be based on scientifically valid methods with...
- Distribution Shift
- In machine learning, distribution shift occurs when the statistical characteristics of data the model encounters in deployment differ from those of the...
- GAN Fingerprint
- A model-specific periodic pattern embedded in GAN-generated images, detectable by averaging outputs and subtracting a reference. Analogous to photo-response non-uniformity (PRNU) in...
- Invisible Watermark
- A signal embedded in an image or audio file that is imperceptible to a human viewer but detectable by an algorithm. In...
- ISO/IEC 17025
- The international standard for testing and calibration laboratories, published jointly by the International Organization for Standardization and the International Electrotechnical Commission. It...
- NIST CFTT
- The National Institute of Standards and Technology Computer Forensics Tool Testing programme. It publishes independent test reports for digital forensic tools, including...
- Out-of-Distribution (OOD) Failure
- The drop in a classifier's accuracy when test samples come from a different statistical distribution than the training data. AI-generated image detectors...
- PRNU
- Photo-Response Non-Uniformity. The per-pixel variation in light sensitivity across a camera sensor, which produces a consistent, device-specific noise pattern in every photograph...
- SWGDE
- Scientific Working Group for Digital Evidence. A US multi-agency body that publishes consensus best-practice documents for digital forensic disciplines, including image authentication,...
Explained in these topics
- AI-Generated Image Detection and ProvenanceCoalition for Content Provenance and Authenticity. An open technical standard for attaching cryptographically signed provenance manifests to media files, recor...
- Standards and Validation Frameworks in Media Forensics