How The ChatGPT Watermark Functions And Why It Could Be Defeated

Posted by

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

ChatGPT is an unbelievable tool that online publishers, affiliates and SEOs all at once love and dread.

Some marketers enjoy it due to the fact that they’re finding brand-new methods to utilize it to produce material briefs, describes and complex articles.

Online publishers hesitate of the possibility of AI content flooding the search results, supplanting expert articles composed by people.

As a result, news of a watermarking feature that unlocks detection of ChatGPT-authored content is also anticipated 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 mostly seen in photographs and increasingly in videos.

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

Scott Aaronson and ChatGPT Watermarking

An influential computer scientist called Scott Aaronson was worked with by OpenAI in June 2022 to work on AI Security and Alignment.

AI Security is a research field concerned with studying ways that AI may present a damage to humans and developing methods to prevent that kind of unfavorable disturbance.

The Distill clinical journal, including authors connected with OpenAI, defines AI Security like this:

“The goal of long-lasting expert system (AI) safety is to guarantee that sophisticated AI systems are reliably aligned with human values– that they dependably do things that individuals desire them to do.”

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

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

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

Aaronson described the reason for watermarking ChatGPT output:

“This could be handy for avoiding academic plagiarism, certainly, but likewise, 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 produced by artificial intelligence is created with a relatively foreseeable pattern of word choice.

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

Changing the pattern of the words utilized in produced material is a way to “watermark” the text to make it easy for a system to spot 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 regular AI generated 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 presently in usage. However Scott Aaronson at OpenAI is on record mentioning that it is prepared.

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

Most likely watermarking may be introduced in a last variation of ChatGPT or sooner than that.

Scott Aaronson wrote about how watermarking works:

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

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

Aaronson explained further how ChatGPT watermarking works. However initially, it is necessary to comprehend the idea of tokenization.

Tokenization is an action that happens 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 modifications text into a structured kind that can be used in machine learning.

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

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

At its core, GPT is constantly generating a likelihood distribution over the next token to generate, 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 customized version of the distribution, depending upon a parameter called ‘temperature.’

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 very 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 randomly, the concept will be to choose it pseudorandomly, utilizing a cryptographic pseudorandom function, whose key is known only 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 includes a bias that can just be discovered by somebody with the key to decode it.

This is the technical description:

“To illustrate, in the special case that GPT had a lot of possible tokens that it judged equally probable, you might simply pick whichever token maximized g. The option would look consistently random to someone who didn’t know the key, but 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 conversations on social media where some people recommended that OpenAI could keep a record of every output it generates and use that for detection.

Scott Aaronson validates that OpenAI could do that but that doing so poses a privacy problem. The possible exception is for law enforcement scenario, which he didn’t elaborate on.

How to Identify ChatGPT or GPT Watermarking

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

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

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

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

It seems 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 enter usage, it may be unknown if this loophole was closed.

Citation

Read Scott Aaronson’s blog post here.

Included image by Best SMM Panel/RealPeopleStudio