Content provenance & watermarking

Defines C2PA manifests: signed assertions about a media asset's origin and edits. Cryptographic hashes bind a manifest to the content, and fingerprints or invisible watermarks can optionally bind it too.

Community founded by Adobe in 2019 that promotes adoption of C2PA Content Credentials and develops open-source tools for them.

NIST report (AI 100-4) that surveys technical approaches to digital content transparency and their limitations. The approaches include tracking provenance through watermarks and metadata, and detecting synthetic content.

Text watermark that softly favors a pseudorandom set of 'green' tokens at each generation step. A statistical test can detect it without access to the model.

Describes SynthID-Text, a sampling-based text watermark that works with speculative sampling, a technique for faster generation. It also reports a live experiment that assessed nearly 20 million Gemini responses for quality.

Google DeepMind's watermarking for AI-generated images, audio, text and video. Its SynthID Detector portal checks content from Google and from partners including OpenAI, NVIDIA and Kakao.

Fine-tunes a latent diffusion model's decoder so that every generated image carries an invisible watermark that remains detectable after edits such as cropping.

Cryptographic watermark for language models whose outputs cannot be distinguished from the original model's outputs without the secret key.

Proves that strong watermarking of generative model outputs is impossible under stated assumptions. A strong watermark is one that cannot be removed without noticeably degrading output quality. The paper also gives a generic removal attack that worked against three text watermarking schemes.

Voluntary code that helps providers and deployers of generative AI meet the marking and labeling obligations in Article 50 of the EU AI Act. These obligations apply from 2 August 2026. The final version of the code was published on 10 June 2026.

Opt-in iPhone camera mode in which the image sensor signs pixel data at capture. The Secure Enclave, the iPhone's security processor, signs other metadata. Private Cloud Compute then develops the images. Apple contrasts the mode with C2PA-based approaches.

Security write-up on C2PA's exclusion ranges, the parts of a file that a signer may leave out of the signed hash. The author shows that a signer can exclude the whole file. The claim signature and trusted timestamp then cover none of its content, so later edits do not invalidate them.

Chinese rules issued by the Cyberspace Administration of China and three other agencies, in force since 1 September 2025. Providers must add explicit labels, which users can see or hear, to AI-generated content. They must also write implicit labels into its metadata. Distribution platforms must check the metadata and label the content accordingly.

South Korean law in force since 22 January 2026. The link is to the Korea Legislation Research Institute's unofficial English translation. The law requires generative AI outputs to be labeled. AI-generated sounds, images or videos that are hard to tell apart from real ones must be clearly disclosed. The law also sets risk-management duties for AI systems trained above a compute threshold.

Multi-part ISO/IEC standard from the JPEG committee for annotating media assets with information on provenance, authenticity, attribution, rights and integrity. Part 1, Core foundation, was published as ISO/IEC 21617-1:2025 in January 2025. Parts on trust profiles, watermarking and reference software are in development.

C2PA program, launched in mid-2025, that covers generator products, validator products and certification authorities. It holds them to the Content Credentials specification, certificate policy and security requirements. It publishes the Conforming Products List, the C2PA Trust List and a TSA Trust List for time-stamping authorities.

Google's account of Content Credentials in the Pixel 10 camera and Google Photos. Google says the camera app reached Assurance Level 2 of the C2PA Conformance Program through hardware-backed key attestation. It also says the app signs each image with a single-use certificate and timestamps offline captures with an on-device time-stamping authority.

Structured survey, or systematization of knowledge (SoK), on watermarking for AI-generated content. It formalizes the definitions and desired properties of watermarking schemes and examines their objectives and threat models. It also reviews evaluation strategies and representative schemes, and discusses regulatory context and open challenges.

Benchmark for image watermark robustness that combines detection and identification tasks with a standardized set of stress tests. The tests range from common image distortions to diffusion-based and adversarial attacks. After each attack, it measures both the loss of image quality and how well the watermark is still detected.

Open-source toolkit that implements many LLM text watermarking algorithms, including KGW, Unigram and SynthID-Text, behind one interface. It visualizes how they work and provides tools to evaluate detectability, robustness and text quality.

Open-source neural video watermarking method from Meta. It jointly trains an embedder and an extractor, applying transformations such as video compression between them. It propagates watermarks across frames, so not every high-resolution frame has to be watermarked.

Partnership on AI framework, launched in February 2023, that recommends consent, disclosure and transparency practices for builders, creators and distributors of synthetic media. PAI collects case studies from supporters but does not audit or certify them.