Stories
Slash Boxes
Comments

SoylentNews is people

A Watermark for Chatbots can Expose Text Written by an AI

posted by hubie on Tuesday February 14, @11:15PM   Printer-friendly

fliptop writes:

The tool could let teachers spot plagiarism or help social media platforms fight disinformation bots:

Hidden patterns purposely buried in AI-generated texts could help identify them as such, allowing us to tell whether the words we're reading are written by a human or not.

These "watermarks" are invisible to the human eye but let computers detect that the text probably comes from an AI system. If embedded in large language models, they could help prevent some of the problems that these models have already caused.

For example, since OpenAI's chatbot ChatGPT was launched in November, students have already started cheating by using it to write essays for them. News website CNET has used ChatGPT to write articles, only to have to issue corrections amid accusations of plagiarism. Building the watermarking approach into such systems before they're released could help address such problems.

In studies, these watermarks have already been used to identify AI-generated text with near certainty. Researchers at the University of Maryland, for example, were able to spot text created by Meta's open-source language model, OPT-6.7B, using a detection algorithm they built. The work is described in a paper that's yet to be peer-reviewed, and the code will be available for free around February 15.

[...] There are limitations to this new method, however. Watermarking only works if it is embedded in the large language model by its creators right from the beginning. Although OpenAI is reputedly working on methods to detect AI-generated text, including watermarks, the research remains highly secretive. The company doesn't tend to give external parties much information about how ChatGPT works or was trained, much less access to tinker with it. OpenAI didn't immediately respond to our request for comment.

Related:

Original Submission

 
This discussion was created by hubie (1068) for logged-in users only, but now has been archived. No new comments can be posted.
A Watermark for Chatbots can Expose Text Written by an AI | Log In/Create an Account | Top | 5 comments | Search Discussion
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.

  • (Score: 2) by fliptop on Tuesday February 14, @11:58PM

    by fliptop (1666) on Tuesday February 14, @11:58PM (#1291799) Journal

    there will be another tool to obfuscate, scramble and remove it

    Unfortunately, it's another moving target to be dealt w/.

    --
    To be oneself, and unafraid whether right or wrong, is more admirable than the easy cowardice of surrender to conformity
    Starting Score:    1  point
    Karma-Bonus Modifier   +1  
    Total Score:   2