How The ChatGPT Watermark Functions And Why It Could Be Defeated

Posted by

OpenAI’s ChatGPT introduced a method to automatically develop material but plans to introduce a watermarking function to make it easy to identify are making some people anxious. This is how ChatGPT watermarking works and why there might be a way to defeat it.

ChatGPT is an unbelievable tool that online publishers, affiliates and SEOs all at once enjoy and fear.

Some marketers enjoy it due to the fact that they’re discovering brand-new methods to use it to create material briefs, details and complicated posts.

Online publishers are afraid of the prospect of AI material flooding the search results page, supplanting specialist short articles composed by human beings.

As a result, news of a watermarking function that opens detection of ChatGPT-authored material is similarly anticipated 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 initial author of the work.

It’s mainly seen in photographs and significantly in videos.

Watermarking text in ChatGPT involves 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 researcher called Scott Aaronson was worked with by OpenAI in June 2022 to work on AI Security and Positioning.

AI Security is a research field concerned with studying ways that AI might position a damage to human beings and developing ways to prevent that sort of negative interruption.

The Distill scientific journal, including authors associated with OpenAI, specifies AI Safety like this:

“The goal of long-term artificial intelligence (AI) safety is to ensure that sophisticated AI systems are reliably lined up with human values– that they reliably do things that people want them to do.”

AI Alignment is the expert system field interested in making certain that the AI is aligned with the intended objectives.

A big language design (LLM) like ChatGPT can be used in a manner that might go contrary to the objectives of AI Alignment as defined by OpenAI, which is to develop AI that benefits mankind.

Appropriately, the reason for watermarking is to avoid the misuse of AI in a manner that harms humankind.

Aaronson discussed the factor for watermarking ChatGPT output:

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

How Does ChatGPT Watermarking Work?

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

Content developed by expert system is generated with a relatively foreseeable pattern of word choice.

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

Altering the pattern of the words utilized in produced material is a method 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 distribution of words still have a random look comparable to regular AI generated text.

This is described as a pseudorandom distribution of words.

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

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

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

Most likely watermarking might be presented in a last variation of ChatGPT or faster than that.

Scott Aaronson discussed how watermarking works:

“My main task up until now has actually been a tool for statistically watermarking the outputs of a text model like GPT.

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

Aaronson described further how ChatGPT watermarking works. But initially, it is very important to understand the concept of tokenization.

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

Tokenization modifications text into a structured kind that can be used in artificial intelligence.

The procedure of text generation is the machine guessing which token comes next based on the previous token.

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

What word is next is forecasted however it’s random.

The watermarking itself is what Aaron refers to as pseudorandom, in that there’s a mathematical factor for a specific word or punctuation mark to be there but 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 likewise punctuation marks, parts of words, or more– there are about 100,000 tokens in total.

At its core, GPT is continuously producing a possibility distribution over the next token to produce, conditional on the string of previous tokens.

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

As long as the temperature level is nonzero, however, there will generally be some randomness in the choice of the next token: you might run over and over with the very same timely, and get a various completion (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 only to OpenAI.”

The watermark looks entirely 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 bias that can just be spotted by somebody with the key to decipher it.

This is the technical explanation:

“To illustrate, in the diplomatic immunity that GPT had a lot of possible tokens that it evaluated similarly likely, you might simply choose whichever token taken full advantage of g. The choice would look consistently random to somebody who didn’t understand the secret, however somebody who did know the key might later on sum g over all n-grams and see that it was anomalously big.”

Watermarking is a Privacy-first Service

I have actually seen discussions on social networks where some people suggested that OpenAI could keep a record of every output it generates and utilize that for detection.

Scott Aaronson confirms that OpenAI could do that however that doing so positions a privacy problem. The possible exception is for law enforcement circumstance, which he didn’t elaborate on.

How to Spot ChatGPT or GPT Watermarking

Something intriguing that appears to not be popular 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 adequate effort.

For instance, if you used another AI to paraphrase GPT’s output– well all right, we’re not going to be able to detect that.”

It appears like the watermarking can be defeated, a minimum of in from November when the above declarations were made.

There is no indicator that the watermarking is currently in usage. But when it does come into usage, it might be unidentified if this loophole was closed.


Check out Scott Aaronson’s article here.

Included image by Best SMM Panel/RealPeopleStudio