How The ChatGPT Watermark Functions And Why It Might Be Defeated

Posted by

OpenAI’s ChatGPT presented a way to immediately create material but plans to introduce a watermarking feature to make it simple to identify are making some people worried. This is how ChatGPT watermarking works and why there might be a way to beat it.

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

Some marketers love it due to the fact that they’re finding new ways to use it to produce content briefs, lays out and complicated articles.

Online publishers hesitate of the possibility of AI material flooding the search results page, supplanting professional posts written by people.

Consequently, news of a watermarking feature that unlocks detection of ChatGPT-authored material is also prepared for with anxiety and hope.

Cryptographic Watermark

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

It’s mostly seen in photographs and increasingly 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 scientist called Scott Aaronson was hired by OpenAI in June 2022 to deal with AI Safety and Positioning.

AI Security is a research study field worried about studying ways that AI might position a damage to human beings and developing ways to prevent that type of unfavorable disturbance.

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

“The goal of long-lasting expert system (AI) security is to ensure that advanced AI systems are dependably aligned with human values– that they reliably do things that people want them to do.”

AI Positioning is the artificial intelligence field worried about making certain that the AI is lined up with the designated goals.

A large language model (LLM) like ChatGPT can be utilized in such a way that might go contrary to the objectives of AI Alignment as defined by OpenAI, which is to develop AI that advantages humankind.

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

Aaronson discussed the reason for watermarking ChatGPT output:

“This could be handy for preventing academic plagiarism, undoubtedly, however likewise, for instance, 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.

Material produced by expert system is generated with a relatively predictable pattern of word option.

The words written by humans and AI follow an analytical pattern.

Altering the pattern of the words used in created material is a method to “watermark” the text to make it simple for a system to detect if it was the item of an AI text generator.

The technique that makes AI material watermarking undetected is that the distribution of words still have a random look similar to regular AI generated text.

This is referred to as a pseudorandom circulation of words.

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

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

Today ChatGPT is in sneak peeks, which enables OpenAI to discover “misalignment” through real-world use.

Most likely watermarking may be introduced in a last version of ChatGPT or earlier than that.

Scott Aaronson discussed how watermarking works:

“My primary task so far has actually been a tool for statistically watermarking the outputs of a text model like GPT.

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

Aaronson discussed even more how ChatGPT watermarking works. But initially, it’s important to understand the idea of tokenization.

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

Tokenization modifications text into a structured type that can be used in machine learning.

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

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

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

The watermarking itself is what Aaron describes as pseudorandom, in that 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 could be words however also punctuation marks, parts of words, or more– there are about 100,000 tokens in overall.

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

After the neural net produces the circulation, the OpenAI server then really samples a token according to that distribution– or some customized variation of the circulation, depending on a specification called ‘temperature.’

As long as the temperature is nonzero, though, there will generally be some randomness in the choice of the next token: you might run over and over with the exact same prompt, and get a different conclusion (i.e., string of output tokens) each time.

So then to watermark, instead of choosing the next token arbitrarily, the idea will be to choose it pseudorandomly, utilizing a cryptographic pseudorandom function, whose key is understood only to OpenAI.”

The watermark looks totally natural to those checking out the text because the option of words is simulating the randomness of all the other words.

However that randomness contains a predisposition that can just be discovered by someone with the key to translate it.

This is the technical explanation:

“To highlight, in the diplomatic immunity that GPT had a bunch of possible tokens that it evaluated equally likely, you might simply pick whichever token made the most of g. The choice would look consistently random to somebody who didn’t understand the key, but someone 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 Option

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

Scott Aaronson confirms that OpenAI could do that but that doing so poses a privacy issue. The possible exception is for police situation, which he didn’t elaborate on.

How to Spot ChatGPT or GPT Watermarking

Something interesting that appears to not be popular yet is that Scott Aaronson noted that there is a method to beat the watermarking.

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

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

For example, if you used another AI to paraphrase GPT’s output– well all right, we’re not going to have the ability to find that.”

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

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


Read Scott Aaronson’s blog post here.

Included image by Best SMM Panel/RealPeopleStudio