How The ChatGPT Watermark Functions And Why It Might Be Defeated

Posted by

OpenAI’s ChatGPT presented a way to instantly produce content however plans to present a watermarking function to make it easy to detect are making some people nervous. This is how ChatGPT watermarking works and why there might be a way to defeat it.

ChatGPT is an extraordinary tool that online publishers, affiliates and SEOs concurrently enjoy and dread.

Some online marketers enjoy it because they’re finding brand-new ways to utilize it to generate material briefs, lays out and complicated posts.

Online publishers hesitate of the prospect of AI material flooding the search engine result, supplanting professional posts written by human beings.

Subsequently, news of a watermarking feature that unlocks detection of ChatGPT-authored material is likewise expected 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 original author of the work.

It’s mostly seen in pictures and significantly in videos.

Watermarking text in ChatGPT involves cryptography in the form 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 Safety is a research field interested in studying ways that AI may pose a harm to human beings and creating ways to prevent that sort of negative disruption.

The Distill clinical journal, including authors connected with OpenAI, specifies AI Security like this:

“The objective of long-term artificial intelligence (AI) security is to make sure that innovative AI systems are dependably lined up with human worths– that they dependably do things that people desire them to do.”

AI Alignment is the expert system field concerned with making certain that the AI is aligned with the designated goals.

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

Appropriately, the factor for watermarking is to prevent the abuse of AI in such a way that damages humanity.

Aaronson explained the reason for watermarking ChatGPT output:

“This could be helpful for preventing academic plagiarism, certainly, 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 choices of words and even punctuation marks.

Material developed by artificial intelligence is produced with a relatively predictable pattern of word option.

The words composed by human beings and AI follow an analytical pattern.

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

The technique that makes AI material watermarking undetected is that the circulation of words still have a random appearance comparable to regular AI generated text.

This is described as a pseudorandom circulation of words.

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

ChatGPT watermarking is not presently in use. However Scott Aaronson at OpenAI is on record mentioning that it is planned.

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

Probably watermarking may be introduced in a last version of ChatGPT or quicker than that.

Scott Aaronson discussed how watermarking works:

“My main task so far has actually been a tool for statistically watermarking the outputs of a text model 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 show later on that, yes, this came from GPT.”

Aaronson discussed further how ChatGPT watermarking works. However initially, it is necessary to understand the principle 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 utilized in artificial intelligence.

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

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

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

The watermarking itself is what Aaron refers to as pseudorandom, because there’s a mathematical reason for a particular word or punctuation mark to be there but 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 could be words but also punctuation marks, parts of words, or more– there have to do with 100,000 tokens in total.

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

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

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

So then to watermark, rather of picking the next token randomly, the concept will be to choose it pseudorandomly, utilizing a cryptographic pseudorandom function, whose secret is known only to OpenAI.”

The watermark looks totally natural to those reading the text because the choice of words is mimicking the randomness of all the other words.

But that randomness includes a predisposition that can just be identified by someone with the secret to decipher it.

This is the technical explanation:

“To highlight, in the special case that GPT had a bunch of possible tokens that it judged similarly possible, you could merely pick whichever token optimized g. The option would look uniformly random to somebody who didn’t know the secret, however somebody who did know the secret could later on sum g over all n-grams and see that it was anomalously big.”

Watermarking is a Privacy-first Service

I’ve seen discussions on social networks where some people recommended that OpenAI could keep a record of every output it generates and use that for detection.

Scott Aaronson validates that OpenAI could do that however that doing so presents a privacy issue. The possible exception is for police scenario, which he didn’t elaborate on.

How to Detect 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 defeat the watermarking.

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

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

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

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

There is no sign that the watermarking is presently in usage. But when it does come into usage, it may be unidentified if this loophole was closed.


Read Scott Aaronson’s post here.

Included image by Best SMM Panel/RealPeopleStudio