通过内容凭证、SynthID 以及一款早期公开验证工具，帮助人们了解 AI 生成内容的来源。
试用我们的工具
人们每天都在使用 OpenAI 的工具来创作和编辑图像与音频，让沟通更具表现力、更实用、更易获取。随着这些工具成为人们构建、想象和分享的一部分，人们能够了解并验证媒体来源变得至关重要，这样他们才能更有信心地解读这些内容。溯源信号可以提供帮助，让人们了解内容的来源、创作或编辑方式，以及它是否名副其实。
今天，我们正在通过一种多层次、生态驱动的模型来强化内容溯源方法，以建立在线信任。我们通过遵循 C2PA 标准，让我们的溯源信号更易于其他工具和平台识别；通过与 Google 合作，为图像添加持久的跨平台 SynthID 水印；并分享了一款工具的预览版，公众可用它来验证图像是否来自 OpenAI。
这些更新共同建立在我们早期工作的基础之上，以支持开放标准，让 OpenAI 生成的内容更易于识别，并在行业内开展合作，以支持一个更值得信赖的信息生态系统。
通过遵循 C2PA 标准构建信任生态系统
自 2024 年起，OpenAI 就一直参与溯源标准的制定和采用工作，当时我们开始为 DALL·E 3 生成的图像添加内容凭证，后来也为 ImageGen 和 Sora 添加了该功能。我们还加入了内容溯源与真实性联盟（C2PA）的指导委员会，该联盟是一个跨行业组织，负责制定内容溯源开放技术标准。C2PA 的技术方法使用元数据和加密签名，帮助媒体相关信息安全地随内容本身一起传播。这些信息包括有助于记者评估来源、平台做出完整性决策以及人们理解他们在网上所看到内容的背景信息。
我们近期采取了行动，使 OpenAI 成为 C2PA 合规生成产品。通过符合 C2PA 标准，我们为平台提供了一种可信的方式，来读取、保留并传递我们附加在内容上的来源信息。这一点之所以重要，是因为来源信息只有在内容创建后的首个平台之外仍能存续时才有意义，而合规性使这成为可能。
结合 Google SynthID 的多层次图像来源验证方法
C2PA 元数据是来源验证的重要基础。它帮助内容携带关于其来源、创建或编辑方式以及签署该信息者的信息。但元数据并非万无一失。它可能被剥离，在上传和下载过程中丢失，或因文件格式转换、调整大小或截图等变换而损坏。
为了使来源验证更具韧性，我们正在采取多层次方法，并通过 Google DeepMind 的 SynthID 引入水印技术，首先从通过 ChatGPT、Codex 或 OpenAI API 生成的图像开始。SynthID 嵌入了一层不可见的水印，对基于 C2PA 元数据的方法形成补充。
我们为此已经筹备了一段时间。我们已在 Sora 中使用了可见水印，在 Voice Engine 中使用了音频水印，并持续通过部署来测试和研究其准确性与可靠性。
这两个系统相互强化。C2PA 帮助内容携带详细的上下文信息；SynthID 则在元数据无法存续时帮助保留信号。水印在截图等变换过程中更具持久性，而元数据能提供比单独水印更丰富的信息。两者结合，使来源验证比任何单一层次都更具韧性。
检测功能及我们的公开验证工具预览
能够抵抗大多数修改的可信元数据和水印，可以使来源信号更具持久性。但人们需要一种检测这些信号的方法。我们目前正在预览一款公开验证工具，该工具通过检查上传图像是否包含来源信号（包括内容凭证和 SynthID），帮助人们验证该图像是否由 ChatGPT、OpenAI API 或 Codex 生成。
我们认为，溯源信息应当更易于人们验证和理解，我们的工具能够通过整合多种信号，帮助人们在回答“这是否由 AI 生成？”这个问题上发挥作用。这建立在 2024 年我们图像检测分类器初始研究预览的经验之上，使人们能够可靠地检测媒体中是否存在源自 OpenAI 的 SynthID 水印，并在发现 C2PA 元数据时将其呈现出来。
没有任何检测方法是万无一失的，因此我们在检测失败的情况下会采取谨慎态度。例如，如果未检测到元数据或水印，该工具不会对图像是否由 OpenAI 工具生成做出明确结论，因为溯源信号在某些情况下可能会被移除。
在发布时，该工具仅限于检测由 OpenAI 生成的内容。在接下来的几个月里，我们旨在支持跨行业的努力，使验证能够在不同平台上实现。随着时间的推移，我们还期望支持人们可能在网络上遇到的更多类型的内容。
未来展望
没有任何单一的溯源技术能够独立解决问题。我们认为，一个强有力的方法需要结合共享标准、持久的水印信号以及公开验证。通过在我们长期以来对内容凭证（Content Credentials）的支持基础上，遵循 C2PA 标准，采用 SynthID 技术，并预览公开验证工具，我们希望从长远来看，能够为一个更具互操作性的溯源生态系统做出贡献。
Helping people understand the origin of AI-generated content through Content Credentials, SynthID, and an early public verification tool.
Try our tool
People are using OpenAI’s tools everyday to create and edit images and audio in ways that make communication more expressive, useful, and accessible. As these tools become a part of how people build, imagine, and share, it’s important that people can understand and verify where the media comes from so they can interpret it with more confidence. Provenance signals can help by giving people context about where content came from, how it was created or edited, and whether it is what it claims to be.
Today we’re strengthening our approach to content provenance with a multi-layered, ecosystem-driven model to building trust online. We are making our provenance signals easier for other tools and platforms to recognize through C2PA conformance, adding durable cross-platform SynthID watermarking to images through a partnership with Google, and sharing a preview of a tool the public can use to verify whether images came from OpenAI.
Together these updates build on our earlier work to support open standards, make OpenAI-generated content easier to identify, and collaborate across the industry to support a more trustworthy information ecosystem.
Building the trust ecosystem through C2PA conformance
OpenAI has been engaged in the development and adoption of provenance standards since 2024, when we began adding Content Credentials to images generated by DALL·E 3 and later to ImageGen and Sora . We also joined the Steering Committee of the Coalition for Content Provenance and Authenticity (C2PA), the cross-industry group behind the open technical standard for content provenance. C2PA’s technical approach uses metadata and cryptographic signatures to help information about a piece of media securely travel with the content itself. This information includes context that helps journalists evaluating a source, platforms making integrity decisions, and people trying to understand what they are seeing online.
We recently took the step of making OpenAI a C2PA Conforming Generator Product . By becoming C2PA conformant, we are giving platforms a trusted way to read, preserve, and pass along the provenance information we attach to our content. This matters because provenance only works if it survives beyond the first platform where content is created, and conformance makes that possible.
A multi-layered approach to provenance with Google SynthID for images
C2PA metadata is an important foundation for provenance. It helps content carry information about where it came from, how it was created or edited, and who signed that information. But metadata is not foolproof. It can be stripped, lost through uploads and downloads, or broken by transformations like file format changes, resizing, or screenshots.
To make provenance more resilient, we are taking a multi-layered approach and incorporating watermarking through Google DeepMind’s SynthID , starting with images generated through ChatGPT, Codex, or the OpenAI API. SynthID embeds an invisible watermarking layer that complements C2PA metadata-based approaches.
We’ve been building toward this for some time. We have used visible watermarks in Sora and an audio watermark in Voice Engine, and have continued to test and research accuracy and reliability over time. through deployment.
These two systems reinforce each other. C2PA helps content carry detailed context; SynthID helps preserve a signal when metadata does not survive. Watermarking can be more durable through transformations like screenshots, while metadata can provide more information than a watermark alone. Together, they make provenance more resilient than either layer would be on its own.
Detection and a preview of our public verification tool
Trusted metadata and watermarks that resist most modifications can make provenance signals more durable. But people need a way to detect these signals. We are now previewing a public verification tool that will help people verify whether an uploaded image was generated on ChatGPT, the OpenAI API, or Codex, by checking if it contains provenance signals, including Content Credentials and SynthID.
We believe provenance should be easier for people to verify and interpret, and that our tool can help people play a role in answering the question, “Was this generated with AI?” by integrating multiple signals. This builds on learnings from the initial research preview of our image detection classifier in 2024 and enables people to reliably detect whether a SynthID watermark originating from OpenAI is present in the media, as well as surface C2PA metadata when it is found.
No detection method is foolproof, so we take a cautious approach in cases when detection fails. If no metadata or watermark is detected, for example, the tool will not make a definitive conclusion about whether the image was generated with OpenAI tools since provenance signals can in some cases be stripped.
At launch, the tool is limited to content generated by OpenAI. In the upcoming months, we aim to support cross-industry efforts to make verification possible across platforms. Over time, we also expect to support more types of content that people may encounter online.
Looking ahead
No single provenance technique is enough on its own. We believe a strong approach combines shared standards, durable watermarking signals, and public verification. By building on our long-standing support for Content Credentials, becoming conformant with C2PA, adopting SynthID, and previewing public verification tooling, we hope to contribute in the long run to a more interoperable provenance ecosystem.