New ChatGPT Models Seem to Leave Watermarks on Text

Re:New ChatGPT Models Seem to Leave Watermarks on Text by greyface- on Tuesday April 22, 2025 @01:26AM (#43759298)

I remember when $EMPLOYER was caught sending all-employee emails with individualized unicode homoglyph watermarks, to try to identify leaks.

[ Parent | on HN ]

Re:New ChatGPT Models Seem to Leave Watermarks on Text by madars on Tuesday April 22, 2025 @01:34AM (#43759330)

For those unaware of the reference, a famous example was Tesla. HN discussion: https://news.ycombinator.com/item?id=33621562 (Tesla has used space characters in internal emails to identify leaks), see also a general discussion of related techniques: https://en.wikipedia.org/wiki/Canary_trap

[ Parent | on HN ]