How The ChatGPT Watermark Works And Why It Might Be Defeated

Posted by

OpenAI’s ChatGPT introduced a method to automatically create content however prepares to present a watermarking function to make it simple to discover are making some individuals nervous. This is how ChatGPT watermarking works and why there might be a method to defeat it.

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

Some marketers love it due to the fact that they’re finding brand-new methods to utilize it to produce content briefs, details and intricate short articles.

Online publishers hesitate of the possibility of AI content flooding the search engine result, supplanting professional posts composed by people.

Consequently, news of a watermarking function that unlocks detection of ChatGPT-authored content is also 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 largely seen in pictures and significantly 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

An influential computer system researcher named Scott Aaronson was employed by OpenAI in June 2022 to work on AI Safety and Positioning.

AI Safety is a research study field interested in studying manner ins which AI might pose a harm to human beings and producing ways to avoid that sort of negative disruption.

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

“The objective of long-term artificial intelligence (AI) safety is to make sure that sophisticated AI systems are dependably lined up with human values– that they reliably do things that individuals desire them to do.”

AI Alignment is the expert system field concerned with ensuring that the AI is lined up with the intended objectives.

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

Accordingly, the reason for watermarking is to prevent the abuse of AI in a way that damages humanity.

Aaronson explained the factor for watermarking ChatGPT output:

“This could be useful for avoiding academic plagiarism, undoubtedly, but likewise, 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 options of words and even punctuation marks.

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

The words written by human beings and AI follow a statistical pattern.

Altering the pattern of the words used in generated content is a way to “watermark” the text to make it easy for a system to discover if it was the product 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 produced text.

This is referred to 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 usage. Nevertheless Scott Aaronson at OpenAI is on record mentioning that it is prepared.

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

Presumably watermarking may be introduced in a final version of ChatGPT or earlier than that.

Scott Aaronson discussed how watermarking works:

“My primary project so far has been a tool for statistically watermarking the outputs of a text design like GPT.

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

Aaronson described further how ChatGPT watermarking works. However first, it is essential to understand the principle of tokenization.

Tokenization is a step that occurs 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 form that can be used in artificial intelligence.

The procedure of text generation is the machine guessing which token comes next based upon 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 possibility distribution.

What word is next is predicted 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 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 are about 100,000 tokens in overall.

At its core, GPT is continuously generating a likelihood 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 in fact samples a token according to that circulation– or some modified variation of the distribution, depending upon a parameter called ‘temperature.’

As long as the temperature level is nonzero, though, there will usually 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, rather of choosing the next token arbitrarily, the idea will be to select it pseudorandomly, utilizing a cryptographic pseudorandom function, whose secret is known only to OpenAI.”

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

But that randomness contains a predisposition that can only be found by someone with the key to decipher it.

This is the technical explanation:

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

Watermarking is a Privacy-first Option

I have actually seen discussions on social networks where some individuals suggested that OpenAI might keep a record of every output it creates and utilize that for detection.

Scott Aaronson verifies that OpenAI might do that however that doing so poses a personal privacy problem. The possible exception is for police scenario, 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 kept in mind that there is a way to beat the watermarking.

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

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

For instance, if you utilized another AI to paraphrase GPT’s output– well okay, we’re not going to be able to detect that.”

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

There is no indication that the watermarking is presently in use. But when it does enter into use, it might be unidentified if this loophole was closed.

Citation

Read Scott Aaronson’s post here.

Included image by SMM Panel/RealPeopleStudio