News for hackers. Stuff that matters.

A comment on OpenAI Quietly Shuts Down Its AI Detection Tool. Parent comment

Re:OpenAI Quietly Shuts Down Its AI Detection Tool by xattt on Tuesday July 25, 2023 @11:04AM (#36863361)
I see no reason why watermarking can’t be broken by having someone simply rephrase/redraw the output.

Yes, it’s still work, but it’s one step removed from having to think up of the original content.

[ Parent | on HN ]
Re:OpenAI Quietly Shuts Down Its AI Detection Tool by whimsicalism on Tuesday July 25, 2023 @12:44PM (#36865227)
Watermarking was never going to be successful except for the most naive uses.
[ Parent | on HN ]
Re:OpenAI Quietly Shuts Down Its AI Detection Tool by SkyPuncher on Tuesday July 25, 2023 @01:57PM (#36866558)
It can likely work in images where you can make subtle, human-undetectable tweaks across thousands/millions of pixels, each with many possible values.

Nearly impossible across data with a couple hundred characters and dozens to thousands of tokens.

[ Parent | on HN ]
Re:OpenAI Quietly Shuts Down Its AI Detection Tool by whimsicalism on Tuesday July 25, 2023 @03:27PM (#36868027)
right but the non-naive approach would be to add noise or have a dumber model rewrite the image. agreed it is easier with images though
[ Parent | on HN ]