[23186] in Privacy_Forum
[ PRIVACY Forum ] Study: How simple use of typos can disrupt LLM AI
daemon@ATHENA.MIT.EDU (Lauren Weinstein)
Sun Feb 22 12:00:35 2026
Date: Sun, 22 Feb 2026 08:46:20 -0800
From: Lauren Weinstein <lauren@vortex.com>
To: privacy-dist@vortex.com
Message-ID: <20260222164620.GA18882@vortex.com>
Content-Disposition: inline
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Errors-To: privacy-bounces+privacy-forum=mit.edu@vortex.com
Study: How simple use of typos can disrupt LLM AI watermarks
https://www.ndss-symposium.org/ndss-paper/character-level-perturbations-disrupt-llm-watermarks/
- - -
--Lauren--
Lauren Weinstein
lauren@vortex.com (https://www.vortex.com/lauren)
Lauren's Blog: https://lauren.vortex.com
Mastodon: https://mastodon.laurenweinstein.org/@lauren
Signal: By request on need to know basis
Founder: Network Neutrality Squad: https://www.nnsquad.org
PRIVACY Forum: https://www.vortex.com/privacy-info
Co-Founder: People For Internet Responsibility
_______________________________________________
privacy mailing list
https://lists.vortex.com/mailman/listinfo/privacy
