How The ChatGPT Watermark Works And Why It Might Be Defeated

Posted by

OpenAI’s ChatGPT presented a way to immediately create content but prepares to introduce a watermarking feature to make it simple to detect are making some people worried. This is how ChatGPT watermarking works and why there may be a method to defeat it.

ChatGPT is an amazing tool that online publishers, affiliates and SEOs at the same time enjoy and dread.

Some online marketers love it because they’re discovering new methods to utilize it to generate material briefs, details and intricate articles.

Online publishers hesitate of the prospect of AI content flooding the search results, supplanting specialist articles written by human beings.

Consequently, news of a watermarking function that unlocks detection of ChatGPT-authored content is likewise prepared for with anxiety and hope.

Cryptographic Watermark

A watermark is a semi-transparent mark (a logo design or text) that is embedded onto an image. The watermark signals who is the initial author of the work.

It’s largely seen in photographs and progressively in videos.

Watermarking text in ChatGPT includes cryptography in the type of embedding a pattern of words, letters and punctiation in the form of a secret code.

Scott Aaronson and ChatGPT Watermarking

An influential computer system scientist called Scott Aaronson was hired by OpenAI in June 2022 to work on AI Safety and Positioning.

AI Security is a research field interested in studying ways that AI may position a damage to humans and producing methods to prevent that sort of negative disruption.

The Distill clinical journal, featuring authors affiliated with OpenAI, defines AI Safety like this:

“The objective of long-term expert system (AI) security is to guarantee that innovative AI systems are dependably aligned with human values– that they dependably do things that individuals desire them to do.”

AI Alignment is the expert system field interested in ensuring that the AI is lined up with the intended goals.

A large language design (LLM) like ChatGPT can be used in a way that may go contrary to the goals of AI Alignment as specified by OpenAI, which is to produce AI that benefits humankind.

Appropriately, the factor for watermarking is to avoid the abuse of AI in a way that damages humankind.

Aaronson explained the reason for watermarking ChatGPT output:

“This could be handy for preventing scholastic plagiarism, obviously, but likewise, for example, mass generation of propaganda …”

How Does ChatGPT Watermarking Work?

ChatGPT watermarking is a system that embeds a statistical pattern, a code, into the options of words and even punctuation marks.

Material created by expert system is created with a fairly foreseeable pattern of word choice.

The words composed by human beings and AI follow a statistical pattern.

Altering the pattern of the words utilized in created content is a method to “watermark” the text to make it simple for a system to identify if it was the product of an AI text generator.

The technique that makes AI content watermarking undetected is that the circulation of words still have a random look comparable to typical AI created text.

This is described as a pseudorandom distribution of words.

Pseudorandomness is a statistically random series of words or numbers that are not in fact random.

ChatGPT watermarking is not currently in usage. Nevertheless Scott Aaronson at OpenAI is on record specifying that it is prepared.

Today ChatGPT remains in previews, which enables OpenAI to find “misalignment” through real-world usage.

Probably watermarking might be presented in a final variation of ChatGPT or faster than that.

Scott Aaronson wrote about how watermarking works:

“My main task so far has been a tool for statistically watermarking the outputs of a text design like GPT.

Essentially, whenever GPT creates some long text, we desire there to be an otherwise undetectable secret signal in its choices of words, which you can use to prove later that, yes, this originated from GPT.”

Aaronson discussed further how ChatGPT watermarking works. However initially, it’s important to comprehend the principle of tokenization.

Tokenization is an action that takes place in natural language processing where the machine takes the words in a file and breaks them down into semantic systems like words and sentences.

Tokenization changes text into a structured type that can be used in artificial intelligence.

The process of text generation is the maker guessing which token comes next based on the previous token.

This is done with a mathematical function that identifies the possibility of what the next token will be, what’s called a probability distribution.

What word is next is anticipated but it’s random.

The watermarking itself is what Aaron refers to as pseudorandom, because there’s a mathematical factor for a specific word or punctuation mark to be there however it is still statistically random.

Here is the technical description of GPT watermarking:

“For GPT, every input and output is a string of tokens, which might be words but also punctuation marks, parts of words, or more– there are about 100,000 tokens in overall.

At its core, GPT is constantly generating a likelihood distribution over the next token to generate, conditional on the string of previous tokens.

After the neural net generates the circulation, the OpenAI server then really samples a token according to that circulation– or some customized version of the distribution, depending upon a criterion called ‘temperature.’

As long as the temperature level is nonzero, however, there will typically be some randomness in the choice of the next token: you could run over and over with the very same timely, and get a different conclusion (i.e., string of output tokens) each time.

So then to watermark, instead of selecting the next token randomly, the concept will be to pick it pseudorandomly, using a cryptographic pseudorandom function, whose secret is known just to OpenAI.”

The watermark looks completely natural to those reading the text since the option of words is imitating the randomness of all the other words.

But that randomness contains a predisposition that can only be discovered by somebody with the secret to translate it.

This is the technical explanation:

“To illustrate, in the diplomatic immunity that GPT had a bunch of possible tokens that it judged equally possible, you could simply select whichever token maximized g. The choice would look evenly random to someone who didn’t know the secret, but someone who did know the key could later sum g over all n-grams and see that it was anomalously big.”

Watermarking is a Privacy-first Option

I’ve seen conversations on social media where some individuals recommended that OpenAI might keep a record of every output it generates and utilize that for detection.

Scott Aaronson confirms that OpenAI might do that but that doing so presents a personal privacy problem. The possible exception is for police circumstance, which he didn’t elaborate on.

How to Spot ChatGPT or GPT Watermarking

Something intriguing that appears to not be well known yet is that Scott Aaronson noted that there is a method to beat the watermarking.

He didn’t state it’s possible to defeat the watermarking, he stated that it can be defeated.

“Now, this can all be defeated with sufficient effort.

For instance, if you used another AI to paraphrase GPT’s output– well fine, we’re not going to have the ability to identify that.”

It looks like the watermarking can be beat, at least in from November when the above statements were made.

There is no indicator that the watermarking is presently in usage. However when it does come into use, it may be unknown if this loophole was closed.


Read Scott Aaronson’s article here.

Featured image by Best SMM Panel/RealPeopleStudio