How The ChatGPT Watermark Works And Why It Might Be Defeated

Posted by

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

ChatGPT is an unbelievable tool that online publishers, affiliates and SEOs at the same time love and fear.

Some marketers enjoy it because they’re discovering new methods to use it to produce material briefs, outlines and intricate short articles.

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

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

Cryptographic Watermark

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

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

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

Scott Aaronson and ChatGPT Watermarking

An influential computer system researcher named Scott Aaronson was hired by OpenAI in June 2022 to deal with AI Safety and Positioning.

AI Safety is a research study field interested in studying manner ins which AI may present a damage to human beings and creating methods to avoid that kind of unfavorable disruption.

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

“The objective of long-term expert system (AI) safety is to ensure that innovative AI systems are reliably lined up with human worths– that they reliably do things that individuals want them to do.”

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

A big language model (LLM) like ChatGPT can be used in a way that may go contrary to the objectives of AI Positioning as defined by OpenAI, which is to develop AI that benefits humanity.

Accordingly, the reason for watermarking is to prevent the misuse of AI in a manner that damages humankind.

Aaronson described the factor for watermarking ChatGPT output:

“This could be useful for preventing scholastic plagiarism, certainly, 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.

Content produced by expert system is created with a fairly predictable pattern of word choice.

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

Altering the pattern of the words utilized in generated content is a way to “watermark” the text to make it easy for a system to find if it was the item of an AI text generator.

The technique that makes AI material watermarking undetectable is that the distribution of words still have a random appearance comparable to regular 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 actually random.

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

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

Probably watermarking might be introduced in a final variation of ChatGPT or sooner than that.

Scott Aaronson wrote about how watermarking works:

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

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

Aaronson explained even more how ChatGPT watermarking works. But first, it’s important to understand the principle of tokenization.

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

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

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

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

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

The watermarking itself is what Aaron describes 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 could be words but likewise punctuation marks, parts of words, or more– there have to do with 100,000 tokens in total.

At its core, GPT is continuously creating a probability distribution over the next token to create, conditional on the string of previous tokens.

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

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

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

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

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

This is the technical description:

“To show, in the special case that GPT had a lot of possible tokens that it evaluated equally likely, you could just select whichever token taken full advantage of g. The option would look uniformly random to someone who didn’t know the key, however 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 Solution

I have actually seen discussions on social media where some individuals recommended that OpenAI could keep a record of every output it generates and use that for detection.

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

How to Discover ChatGPT or GPT Watermarking

Something interesting that seems to not be popular yet is that Scott Aaronson noted that there is a way to defeat the watermarking.

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

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

For example, if you used another AI to paraphrase GPT’s output– well all right, we’re not going to be able 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 indication that the watermarking is currently in use. However when it does come into usage, it may be unidentified if this loophole was closed.

Citation

Check out Scott Aaronson’s blog post here.

Included image by Best SMM Panel/RealPeopleStudio