conv.

← The whole story
AI
Study: EU-mandated AI watermarking weakens model safety refusals

Lasso Security finds watermarking causes 'sampling drift' in agents

1 Sep 17 9:00 AM · 9d ago · 1 article · 1 source · development 1 of 3

Lasso Security published "The Provenance Tax," testing SynthID-Text's non-distortionary configuration across seven open-weight models and finding it reduced tool-calling accuracy on six of them (using BFCL v4) and measurably changed refusal behavior, a phenomenon it calls sampling drift.

Lasso Security finds watermarking causes 'sampling drift' in agents
arstechnica.com

“Watermarking is designed for provenance, but SynthID-Text changes the process by which the model generates each next token.”

Lasso Security

Lasso Security AI security research firmAndrea Siposova AI security researcher at Lasso SecurityAnthropic AI company deploying watermarking in ClaudeGoogle DeepMind Creator of SynthID-Text watermarking method

The whole story articlesposts the bright band is this development · numbered dots are the others · click one to jump

Peak 5 pieces in 3h at Sep 17, 11 AM; 15 pieces over 9 days (2 articles · 13 posts) Sep 17, 8 AM — 1 piece · 1 article — Newswires 1Sep 17, 11 AM — 5 pieces · 1 article · 4 posts — Mastodon 2, Hacker News 1, Bluesky 1, +1 moreSep 17, 2 PM — quietSep 17, 5 PM — 1 piece · 1 post — Mastodon 1Sep 17, 8 PM — quietSep 17, 11 PM — 1 piece · 1 post — Hacker News 1Sep 18, 2 AM — 2 pieces · 2 posts — Hacker News 1, Mastodon 1Sep 18, 5 AM — quietSep 18, 8 AM — quietSep 18, 11 AM — 1 piece · 1 post — Mastodon 1Sep 18, 2 PM — quietSep 18, 5 PM — quietSep 18, 8 PM — quietSep 18, 11 PM — quietSep 19, 2 AM — quietSep 19, 5 AM — quietSep 19, 8 AM — 2 pieces · 2 posts — Bluesky 1, Mastodon 1Sep 19, 11 AM — 1 piece · 1 post — Bluesky 1Sep 19, 2 PM — quietSep 19, 5 PM — quietSep 19, 8 PM — quietSep 19, 11 PM — quietSep 20, 2 AM — quietSep 20, 5 AM — quietSep 20, 8 AM — quietSep 20, 11 AM — quietSep 20, 2 PM — quietSep 20, 5 PM — quietSep 20, 8 PM — 1 piece · 1 post — Bluesky 1Sep 20, 11 PM — quietSep 21, 2 AM — quietSep 21, 5 AM — quietSep 21, 8 AM — quietSep 21, 11 AM — quietSep 21, 2 PM — quietSep 21, 5 PM — quietSep 21, 8 PM — quietSep 21, 11 PM — quietSep 22, 2 AM — quietSep 22, 5 AM — quietSep 22, 8 AM — quietSep 22, 11 AM — quietSep 22, 2 PM — quietSep 22, 5 PM — quietSep 22, 8 PM — quietSep 22, 11 PM — quietSep 23, 2 AM — quietSep 23, 5 AM — quietSep 23, 8 AM — quietSep 23, 11 AM — quietSep 23, 2 PM — quietSep 23, 5 PM — quietSep 23, 8 PM — quietSep 23, 11 PM — quietSep 24, 2 AM — quietSep 24, 5 AM — quietSep 24, 8 AM — quietSep 24, 11 AM — quietSep 24, 2 PM — quietSep 24, 5 PM — quietSep 24, 8 PM — quietSep 24, 11 PM — quietYesterday, 2 AM — quietYesterday, 5 AM — quietYesterday, 8 AM — quietYesterday, 11 AM — quietYesterday, 2 PM — quietYesterday, 5 PM — quietYesterday, 8 PM — quietYesterday, 11 PM — quietToday, 2 AM — quietToday, 5 AM — quietToday, 8 AM — quietToday, 11 AM — quiet 1–3
1–3Lasso Security finds watermarking causes…
Sep 18Sep 19Sep 20Sep 21Sep 22Sep 23Sep 24yesterdaynow · 2:51 PM ET

What was reported 1 claim about this development

  1. 1 outlet AI model watermarking changes agent behavior

    first by The Register, 9d ago

All 3 developments of Study: EU-mandated AI watermarking weakens model safety… →

NewswiresHacker NewsMastodonBluesky