How The ChatGPT Watermark Functions And Why It Could Be Defeated

Posted by

OpenAI’s ChatGPT presented a method to immediately create content but plans to introduce a watermarking function to make it simple to spot are making some individuals nervous. This is how ChatGPT watermarking works and why there might be a method to defeat it.

ChatGPT is an amazing tool that online publishers, affiliates and SEOs concurrently enjoy and fear.

Some online marketers love it because they’re discovering new ways to utilize it to create material briefs, lays out and intricate posts.

Online publishers hesitate of the prospect of AI content flooding the search results, supplanting professional posts composed by people.

Consequently, news of a watermarking feature that opens detection of ChatGPT-authored content is also expected with stress and anxiety and hope.

Cryptographic Watermark

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

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

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

Scott Aaronson and ChatGPT Watermarking

A prominent computer system researcher called Scott Aaronson was hired by OpenAI in June 2022 to work on AI Safety and Alignment.

AI Safety is a research field worried about studying manner ins which AI may present a damage to human beings and developing ways to avoid that kind of unfavorable interruption.

The Distill scientific journal, featuring authors associated with OpenAI, defines AI Security like this:

“The objective of long-lasting expert system (AI) security is to make sure that sophisticated AI systems are reliably lined up with human values– that they dependably do things that people desire them to do.”

AI Positioning is the artificial intelligence field interested in making sure that the AI is lined up with the desired goals.

A large language design (LLM) like ChatGPT can be used in a way that might go contrary to the goals of AI Positioning as specified by OpenAI, which is to develop AI that advantages humanity.

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

Aaronson described the reason for watermarking ChatGPT output:

“This could be useful for avoiding scholastic plagiarism, certainly, but also, for instance, mass generation of propaganda …”

How Does ChatGPT Watermarking Work?

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

Content produced by expert system is generated with a fairly foreseeable pattern of word option.

The words written by humans and AI follow a statistical pattern.

Changing the pattern of the words used in generated content is a way to “watermark” the text to make it simple for a system to spot if it was the product of an AI text generator.

The technique that makes AI material watermarking undetectable is that the circulation of words still have a random appearance similar to regular AI produced 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 use. However Scott Aaronson at OpenAI is on record specifying that it is prepared.

Right now ChatGPT is in sneak peeks, which allows OpenAI to discover “misalignment” through real-world use.

Presumably watermarking may be presented in a last variation of ChatGPT or sooner than that.

Scott Aaronson discussed how watermarking works:

“My primary project up until now has actually been a tool for statistically watermarking the outputs of a text design like GPT.

Basically, whenever GPT produces some long text, we want there to be an otherwise undetectable secret signal in its choices of words, which you can utilize to prove later that, yes, this came from GPT.”

Aaronson described even more how ChatGPT watermarking works. However first, it is necessary to understand the concept of tokenization.

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

Tokenization modifications text into a structured kind that can be utilized in machine learning.

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

This is finished with a mathematical function that identifies the likelihood of what the next token will be, what’s called a possibility circulation.

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 reason for a specific word or punctuation mark to be there however it is still statistically random.

Here is the technical explanation of GPT watermarking:

“For GPT, every input and output is a string of tokens, which might be words however likewise punctuation marks, parts of words, or more– there have to do with 100,000 tokens in total.

At its core, GPT is constantly creating a possibility circulation over the next token to create, conditional on the string of previous tokens.

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

As long as the temperature is nonzero, however, there will normally be some randomness in the option of the next token: you could run over and over with the same timely, and get a various completion (i.e., string of output tokens) each time.

So then to watermark, rather of picking the next token arbitrarily, the concept will be to choose it pseudorandomly, using a cryptographic pseudorandom function, whose key is known just to OpenAI.”

The watermark looks completely natural to those reading the text due to the fact that the choice of words is mimicking the randomness of all the other words.

But that randomness contains a predisposition that can just be found by somebody with the key to translate it.

This is the technical description:

“To illustrate, in the diplomatic immunity that GPT had a lot of possible tokens that it evaluated equally possible, you might just select whichever token taken full advantage of g. The option would look uniformly random to somebody who didn’t know the secret, but someone who did know the secret might later on sum g over all n-grams and see that it was anomalously big.”

Watermarking is a Privacy-first Solution

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

Scott Aaronson confirms that OpenAI might do that however that doing so positions a privacy concern. The possible exception is for police situation, which he didn’t elaborate on.

How to Identify ChatGPT or GPT Watermarking

Something fascinating that seems to not be well known yet is that Scott Aaronson kept in mind that there is a way to beat the watermarking.

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

“Now, this can all be beat with enough effort.

For example, if you used another AI to paraphrase GPT’s output– well alright, we’re not going to be able to discover that.”

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

There is no indication that the watermarking is currently in usage. But when it does enter into use, it might be unknown if this loophole was closed.


Read Scott Aaronson’s post here.

Featured image by Best SMM Panel/RealPeopleStudio