What is the OpenAI ChatGPT watermark?

Patrick Devaney
Jan 1, 2023
Updated • Dec 30, 2022
Misc
|
5

OpenAI has begun discussing the possibility of using a cryptographic watermark in ChatGPT text output that it will make it easier to spot text that has been created by the AI chatbot. The idea is to make sure that the tool isn’t being misused in ways that it shouldn’t such as to write papers for school or college.

What is the OpenAI ChatGPT watermark

A cryptographic watermark is a type of digital watermark that is embedded in a digital file or signal using cryptographic techniques. Digital watermarks are used to identify the ownership or origin of a digital file or signal, and they are often used to protect against unauthorized use or distribution of digital content. You get a lot of these types of watermarks in photos and videos, but OpenAI is talking about developing a cryptographic watermark that is integrated into the text that ChatGPT is outputting.

If you’re thinking about how this would work without affecting the coherence of the text output, you are on the right track, but the reality is that text is so open and infinite that it is very possible to include unnoticeable cryptographic code without it affecting the way the text reads.

In-truth, AI-generated content follows a predictable pattern in the way it uses words, which means that it is fairly easy to recognize it if you know what to look for. However, OpenAI looks set to build in a deliberate element of this predictability in an imperceptible way. As discussed in the Search Engine Journal by OpenAI’s Scott Aaronson, who has been tasked with securing AI Safety and Alignment at the company, this process is called pseudorandom distribution. Pseudorandomness is when a series of words or numbers appear random but is actually not truly random. This allows us to mark AI-generated content without disrupting the appearance of the text. Aaronson has written about the work he is doing o this for OpenAI in his own blog, saying:

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

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

Interestingly, however, it looks as though a simple way to get around this type of watermarking would be to run the text through another generative text AI protocol and ask it to rewrite the text. This might sound silly, but it would offer the user the chance to generate text, removing the need to write it themselves and then sidestep the potential safety feature by having the other protocol write out the cryptographic watermark.

Clearly then, this is still a work in progress, which is likely why for now at least, OpenAI isn’t actively watermarking the text output coming from ChatGPT. However, if you are planning on using ChatGPT to write some important text for you, be careful as, like we mentioned above, if you know what to look for you will be able to spot AI-generated text, even without having a specific watermark to look for.

Summary
What is the OpenAI ChatGPT watermark?
Article Name
What is the OpenAI ChatGPT watermark?
Description
With ChatGPT seemingly make it easier than ever to produce manuscripts and essays, the question is whether there any potential safeguards that could protect against misuse.
Author
Publisher
Ghacks Technology News
Logo
Advertisement

Tutorials & Tips


Previous Post: «
Next Post: «

Comments

  1. Anonymous said on January 2, 2023 at 2:09 am
    Reply

    This is ridiculous. RIP ChatGPT. Hopefully someone comes out with an open-source solution.

    1. boris said on January 2, 2023 at 6:51 am
      Reply

      This “AI” enterprise, in my personal opinion, cost too much money to build and maintain to just giving stuff for free. I bet ChatGPT will start charging people in near future and make more effort to prevent illegal use of service.

      Maybe if a future where ChatGPT is become near monopoly, governments would force OpenAI to disclose part of its code. This way ChatGPT becomes like Windows or Android and other companies will make programs/apps on top of it.

  2. boris said on January 2, 2023 at 12:14 am
    Reply

    How about coping results into text file. Does file format allow you to do that?

    1. boris said on January 2, 2023 at 12:19 am
      Reply

      Sorry did not read article carefully. Interesting way to watermark file without using usual watermark.

      One more task for teachers to check every essay.

  3. John G. said on January 1, 2023 at 11:48 pm
    Reply

    Thanks @Patrick for the article. :]

Leave a Reply

Check the box to consent to your data being stored in line with the guidelines set out in our privacy policy

We love comments and welcome thoughtful and civilized discussion. Rudeness and personal attacks will not be tolerated. Please stay on-topic.
Please note that your comment may not appear immediately after you post it.