How The ChatGPT Watermark Works And Why It Could Be Defeated

Posted by

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

ChatGPT is an amazing tool that online publishers, affiliates and SEOs simultaneously love and dread.

Some online marketers enjoy it because they’re finding brand-new methods to utilize it to generate content briefs, outlines and intricate articles.

Online publishers hesitate of the prospect of AI material flooding the search results, supplanting professional short articles written by people.

Subsequently, news of a watermarking function that unlocks detection of ChatGPT-authored content is similarly expected 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 largely seen in photos and significantly in videos.

Watermarking text in ChatGPT involves cryptography in the type 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 employed by OpenAI in June 2022 to deal with AI Safety and Positioning.

AI Safety is a research field interested in studying manner ins which AI may position a harm to humans and creating ways to prevent that kind of unfavorable disruption.

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

“The objective of long-term expert system (AI) safety is to guarantee that advanced AI systems are reliably aligned with human values– that they dependably do things that individuals want them to do.”

AI Positioning is the artificial intelligence field interested in making certain that the AI is aligned with the designated objectives.

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

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

Aaronson discussed the factor for watermarking ChatGPT output:

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

How Does ChatGPT Watermarking Work?

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

Content created by expert system is generated with a fairly foreseeable pattern of word choice.

The words written by people and AI follow a statistical pattern.

Changing the pattern of the words used in produced material is a method to “watermark” the text to make it easy for a system to find if it was the item of an AI text generator.

The trick that makes AI material watermarking undetected is that the circulation of words still have a random appearance comparable to regular AI produced 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 currently in use. Nevertheless Scott Aaronson at OpenAI is on record stating that it is prepared.

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

Presumably watermarking might be presented in a final variation of ChatGPT or sooner than that.

Scott Aaronson blogged about how watermarking works:

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

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

Aaronson discussed even more how ChatGPT watermarking works. But initially, it is essential to understand the concept of tokenization.

Tokenization is a step that happens in natural language processing where the machine takes the words in a document 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 procedure of text generation is the maker thinking which token follows based on 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 but 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 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 have to do with 100,000 tokens in total.

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

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

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

So then to watermark, instead of picking the next token randomly, the concept will be to select it pseudorandomly, using a cryptographic pseudorandom function, whose key is understood just to OpenAI.”

The watermark looks entirely natural to those reading the text since the option of words is mimicking the randomness of all the other words.

However that randomness contains a predisposition that can only be spotted by someone with the secret to decode it.

This is the technical description:

“To show, in the special case that GPT had a lot of possible tokens that it judged equally likely, you might simply pick whichever token maximized g. The option would look uniformly random to someone who didn’t know the key, but someone who did understand the key might later on sum g over all n-grams and see that it was anomalously large.”

Watermarking is a Privacy-first Service

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

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

How to Discover ChatGPT or GPT Watermarking

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

He didn’t state it’s possible to defeat the watermarking, he said 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 be able to detect that.”

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

There is no sign that the watermarking is currently in usage. However when it does come into use, 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