OpenAI Launches AI Watermarking for ChatGPT in EU, But Detection Remains Vulnerable to Simple Edits
25 Sources
[1]
OpenAI will watermark ChatGPT outputs by default -- but only in the EU
OpenAI will begin automatically watermarking text generated with ChatGPT in the European Union, the company has announced. It will also offer the watermarking feature in other regions, but it will be off by default outside of the EU. The move in Europe is driven by a need to comply with the EU AI
[2]
OpenAI will start watermarking ChatGPT's text in the EU
OpenAI will start adding an invisible watermark to text generated by ChatGPT and Codex in the European Union to comply with the EU AI Act, the company said Monday in a blog post. The EU AI Act's transparency rules, which took effect on August 2, require AI companies to mark AI-generated content in
[3]
OpenAI is adding text watermarking in ChatGPT and Codex
An invisible, machine-readable watermark in text output is rolling out to ChatGPT and Codex, but only for users in the European Union at first. OpenAI says its textGrain watermarking "matched or exceeded" other approaches like Google DeepMind's SynthID for text, which is also the basis for the
[4]
OpenAI to Add Watermarks on ChatGPT's Text Outputs, But Only in the EU
ChatGPT will start including an "invisible watermark" on text outputs to comply with European Union regulations, OpenAI announced on Monday, but it will only apply to users in the EU. "In the EU, we'll start watermarking eligible text from ChatGPT and Codex over the coming weeks to comply with the
[5]
OpenAI rolls out weak sauce watermarking for AI text
OpenAI is now offering API customers the option to watermark the output of certain models in order to comply with the letter of Europe's AI Act. And within a few weeks, the biz plans to apply a form of digital watermarking - like it or not - to eligible ChatGPT and Codex text output in the European
[6]
OpenAI is adding invisible watermarks to ChatGPT and Codex text in the EU
OpenAI is preparing to add invisible watermarks to text generated by ChatGPT and Codex in the European Union. The watermark will not be visible when you read or copy the text. Instead, OpenAI says its new textGrain technology slightly changes the model's word choices to create a statistical
[7]
OpenAI will add a digital watermark to text and code generated in the EU - Engadget
OpenAI just announced its plans to comply with part of the European Union's new AI transparency rules. The company will soon begin adding an invisible watermark to text and code generated in the EU. This follows a similar move by Anthropic earlier this year. OpenAI is using a proprietary system
[8]
ChatGPT users, your AI-written text will soon carry a hidden watermark
For years, AI tools have made it easy to generate everything from images and audio to human-like text. While AI-generated images, videos, and audio can often be identified using dedicated detection tools, AI-written text has largely escaped the same level of scrutiny. ChatGPT, in particular, has
[9]
OpenAI brings text watermarking to ChatGPT and Codex in the EU
Its own tests show editing the text weakens detection. Text watermarking stays opt-in for API customers worldwide, and the detector is limited to approved researchers. OpenAI will add an invisible watermark to text from ChatGPT and Codex in the EU over the coming weeks. The change covers eligible
[10]
OpenAI Is Adding Text Watermarks in the EU Because Regulation Works
Passing off ChatGPT's work as your own is about to get tougher -- at least if you live in the European Union. On Monday, OpenAI announced that it would start inserting an invisible watermark, imperceptible to the naked eye but identifiable by machine, into all text outputs generated by its AI
[11]
OpenAI adds invisible watermarks to ChatGPT text under EU rules
OpenAI will begin adding invisible watermarks to text generated by ChatGPT and Codex in the European Union. The rollout addresses transparency requirements under the EU AI Act. The system embeds a hidden statistical signal into model-generated writing. Readers will not see the watermark, but
[12]
OpenAI details new text watermarking system for ChatGPT, Codex, API
OpenAI today announced how it will comply with the EU AI Act, which requires providers of generative AI systems to mark AI-generated text in a way that makes it identifiable. Here are the details. A bit of context A few months ago, Anthropic sparked controversy when it announced that, to comply
[13]
OpenAI is adding an invisible watermark to AI-generated text
OpenAI is adding an invisible watermark to text generated by ChatGPT and programming agent Codex, making it easier for machines to identify that it was written by AI. Announced on Monday, the change will be mandatory in the EU, and is currently opt-in for API customers across the rest of the
[14]
OpenAI to watermark AI-generated text in EU
AI watermarking is an unreliable technology with 'significant limitations', OpenAI said. OpenAI is rolling out text watermarking in the EU in its latest attempt to comply with the region's AI laws after the bloc said it will regulate ChatGPT under its strictest rules for online platforms. The
[15]
OpenAI will watermark ChatGPT and Codex output in Europe
OpenAI announced plans to add invisible digital watermarks to text and code generated in the European Union to comply with the region's new AI transparency rules. Article 50 of the EU AI Act requires generative AI providers to make text outputs identifiable in a machine-readable way. The
[16]
OpenAI Is Rolling Out Its New AI Watermarking Feature in a Smart Way. Here's How It Differs From Anthropic
OpenAI just revealed how it will comply with European Union regulations on flagging AI content. Compared to the controversial method Anthropic recently implemented, there's a lot going for OpenAI's so-called "text provenance" system -- starting with the way developers can actually test to see how
[17]
ChatGPT-Generated Text Will Soon Show an Invisible Watermark
Editing AI-generated text will reduce the effectiveness of the watermark OpenAI is all set to introduce invisible watermarks for text generated by its AI models. This latest move will make it easier for readers to identify AI-generated content. This feature will be initially available in the
[18]
ChatGPT starts exposing writers using AI with invisible watermarks; OpenAI says its texts, codes can be traced; how to avoid detection
OpenAI is rolling out invisible text watermarking for eligible ChatGPT and Codex output in the European Union, allowing its detector to look for a statistical signal hidden in the model's word choices. The technology can identify many longer passages, but OpenAI says editing, translation, short
[19]
OpenAI Unveils ChatGPT Watermarking
OpenAI Unveils ChatGPT Watermarking as European Union AI Rules Take Effect OpenAI will begin rolling out technology to identify AI-generated text in the European Union as new transparency requirements under the EU AI Act take effect. The company said in a blog post that API developers worldwide
[20]
OpenAI Rolls Out Text Watermarks to Meet EU AI Act Mandates | PYMNTS.com
OpenAI built the technologies in response to the European Union's AI Act, which requires generative artificial intelligence providers to make AI-generated text identifiable in a machine-readable way, according to the article. OpenAI is enabling API customers globally to opt in to text watermarking
[21]
OpenAI textGrain watermarking for ChatGPT and Codex to roll out in EU
OpenAI has announced its approach to text provenance in response to the EU AI Act, which requires generative AI providers to make generated text identifiable in a machine-readable way. The company says its phased approach reflects both the requirements of the regulation and the limitations of
[22]
OpenAI Watermarks ChatGPT and Codex: What Changes for EU Use
Join the DZone community and get the full member experience. Join For Free ChatGPT responses in Europe may soon carry a signal users cannot see. OpenAI is rolling out invisible text watermarks for eligible ChatGPT and Codex output in the European Union across all plans. The provenance system is
[23]
OpenAI to watermark AI-generated text in EU, but detection has limits - MEDIANAMA
OpenAI has announced its approach to text watermarking under the EU AI Act, saying it will use an invisible statistical watermark to help identify text generated by its models. The company said on October 5 that it will begin adding the watermark to eligible ChatGPT and Codex text outputs in the
[24]
OpenAI adds invisible watermarks to ChatGPT and launches a detector for texts generated by AI
OpenAI has announced changes to ChatGPT to comply with the European Union's AI Act. The company will start adding an invisible watermark to ChatGPT and Codex texts, after Anthropic announced a similar system for Claude a couple of weeks ago. An invisible signal between the words ChatGPT
[25]
OpenAI textGrain Watermark: No watermark doesn't mean human written
Substitute one in four words in a response generated by ChatGPT with a synonym, and the new OpenAI system will detect the watermark with an accuracy of around 17 percent. This comes straight from OpenAI's own numbers based on the test performed on passages comprising 400 tokens. On October 5,
Share
Copy Link
OpenAI will watermark ChatGPT and Codex outputs in the European Union to comply with the EU AI Act's transparency requirements. The company's textGrain method achieves 92% detection in tests, but editing just 10% of the text drops accuracy to 66%. Unlike rival Anthropic, OpenAI keeps watermarking off by default outside Europe.
OpenAI Deploys AI Watermarking to Meet EU AI Act Requirements
OpenAI announced it will automatically watermark text generated by ChatGPT and Codex for users in the European Union, marking a significant step toward compliance with the EU AI Act
1
2
. The transparency rules, which took effect on August 2, require AI companies to mark AI-generated content in ways other systems can identify2
. The invisible watermark will roll out over the coming weeks to eligible ChatGPT and Codex users on all plans within the European Union2
3
. Outside the EU, the AI text watermarking feature remains off by default, though developers using OpenAI's API anywhere in the world can activate it for select models2
4
.
Source: Gadgets 360
How textGrain Creates Detectable AI-Generated Content
OpenAI's proprietary method, called textGrain, works by adding an invisible statistical signal to the model's word choices
1
5
. The watermark subtly shapes word selections, leaving patterns human readers cannot see but specialized detectors can identify using a secret key2
. Co-written with researchers from the University of Pennsylvania and Yale, OpenAI published a technical paper explaining how large language models predict word tokens one at a time from a probability distribution, and by periodically selecting different words—ideally synonyms—the resulting text deviates from the statistical pattern produced by an unbiased model output2
5
. Because the watermark lives in the words themselves, it travels with the text when copied and pasted2
. OpenAI claims textGrain matched or exceeded other approaches like Google DeepMind's SynthID for text, which forms the basis for watermarking that Anthropic announced in August3
.
Source: Gizmodo
Detection Accuracy Drops Sharply With Minor Text Modifications
While OpenAI's best-case tests show a 92% successful detection rate, the system's vulnerability to simple editing raises questions about its practical effectiveness for compliance with the EU AI Act
1
. Changing just 10% of the text in ChatGPT outputs reduces successful detection by almost 30 percentage points—from 92% to 66%1
2
. Replacing 20% of words with synonym substitution can lower the success rate by almost 75%, and when 25% of words are swapped, the watermark signal could only be detected in 17% of cases1
5
. Detection rates are also lower for shorter passages, with 200-word texts flagged only 80% of the time compared to 95% for 400-word passages5
. The results are worse in functional texts involving math or code, where substitutions are more likely to introduce errors5
.Related Stories
Limited Detector Access and Cautious Rollout Strategy
OpenAI will provide access to AI detectors only to a limited number of researchers and expert organizations, with a request-for-approval process for others to be added over time
1
2
. The company stated these limitations contribute to its decision to restrict initial detector access, allowing approved parties to evaluate reliability and responsible uses2
. OpenAI cautioned that a missing watermark does not prove human authorship, as the text could be too short, too heavily edited, or generated by another company's generative AI system2
. The company emphasized that watermarks can indicate an OpenAI system generated or processed part of a passage, but not how much human judgment, editing, or creativity went into it2
. OpenAI argues its regional approach gives the company room to learn from real-world use and feedback4
.Diverging Approaches: OpenAI Versus Anthropic on Global Implementation
Unlike Anthropic, which enabled machine-readable watermarking globally in August, OpenAI is currently making the invisible watermark default only where regulators require it
1
3
. Anthropic's decision to watermark text generated by Claude worldwide drew backlash from some users who argued they had supplied the instructions, context, and decisions while Claude was just the tool2
. Anthropic explained it applied watermarking globally because it doesn't yet have a durable way to scope it by region, citing the EU regulation's mention of preventing potential circumvention4
. OpenAI had previously built a text watermark but held off on releasing it, partly over concerns that users would switch to rivals that didn't watermark, The Wall Street Journal reported in 20242
. Both Anthropic and OpenAI are among the companies—including Google, Meta, and Microsoft—that have committed to following the European Union's code of practice on AI-generated content2
.References
Summarized by
Navi
[2]
[5]
Related Stories
Claude AI Rolls Out Invisible Text Watermarks as EU AI Act Deadline Approaches
03 Sept 2026•Technology
OpenAI's Cautious Approach to AI Detection Tools: Balancing Innovation and Responsibility
05 Aug 2024
AI Watermarking Defeated in Hours as Anthropic Claude's Text Labels Face Instant Workarounds
19 Aug 2026•Policy and Regulation
Recent Highlights
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
