How The ChatGPT Watermark Functions And Why It Could Be Defeated

Posted by

OpenAI’s ChatGPT introduced a way to immediately develop content but plans to introduce a watermarking function to make it easy to identify are making some people nervous. This is how ChatGPT watermarking works and why there may be a way to beat it.

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

Some online marketers enjoy it because they’re finding new methods to utilize it to produce material briefs, lays out and intricate articles.

Online publishers hesitate of the possibility of AI content flooding the search results, supplanting specialist short articles composed by human beings.

Consequently, news of a watermarking function that unlocks detection of ChatGPT-authored content is likewise prepared for with stress and 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 mainly seen in pictures and increasingly 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

A prominent computer researcher named Scott Aaronson was employed by OpenAI in June 2022 to work on AI Security and Positioning.

AI Security is a research field worried about studying ways that AI may posture a harm to people and creating methods to prevent that sort of unfavorable interruption.

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

“The goal of long-term artificial intelligence (AI) security is to make sure 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 expert system field concerned with making sure that the AI is aligned with the desired objectives.

A big language model (LLM) like ChatGPT can be utilized in a manner that might go contrary to the goals of AI Positioning as defined by OpenAI, which is to create AI that advantages humanity.

Appropriately, the reason for watermarking is to prevent the abuse of AI in a way that hurts humankind.

Aaronson described the reason for watermarking ChatGPT output:

“This could be valuable for avoiding academic plagiarism, certainly, however also, 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 choices of words and even punctuation marks.

Material produced by artificial intelligence is generated 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 used in produced material is a method to “watermark” the text to make it simple for a system to identify 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 similar to typical AI created text.

This is described as a pseudorandom circulation of words.

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

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

Right now ChatGPT is in previews, which enables OpenAI to discover “misalignment” through real-world use.

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

Scott Aaronson blogged about how watermarking works:

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

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

Aaronson described further how ChatGPT watermarking works. But initially, it is necessary to understand the idea of tokenization.

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

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

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

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

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

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

At its core, GPT is continuously generating a likelihood circulation over the next token to produce, 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 modified variation of the circulation, depending on a specification called ‘temperature level.’

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

So then to watermark, instead of picking the next token arbitrarily, the idea will be to pick it pseudorandomly, using a cryptographic pseudorandom function, whose secret is known only to OpenAI.”

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

But that randomness includes a bias that can just be found by someone with the key to translate it.

This is the technical description:

“To highlight, in the diplomatic immunity that GPT had a lot of possible tokens that it evaluated similarly probable, you could merely select whichever token optimized g. The choice would look consistently random to someone who didn’t know the key, but somebody who did understand the secret could later on sum g over all n-grams and see that it was anomalously big.”

Watermarking is a Privacy-first Solution

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

Scott Aaronson verifies that OpenAI might do that but that doing so positions a privacy concern. The possible exception is for law enforcement situation, which he didn’t elaborate on.

How to Find ChatGPT or GPT Watermarking

Something intriguing 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 defeat the watermarking, he said that it can be beat.

“Now, this can all be beat 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 spot that.”

It looks 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 presently in usage. However when it does enter use, it might be unknown if this loophole was closed.

Citation

Read Scott Aaronson’s blog post here.

Featured image by SMM Panel/RealPeopleStudio