cd /news/ai-safety/ai-model-watermarking-changes-agent-… · home topics ai-safety article
[ARTICLE · art-132592] src=theregister.com ↗ pub= topic=ai-safety verified=true sentiment=· neutral

AI model watermarking changes agent behavior

Lasso Security found that watermarking AI models changes agent behavior, producing differences in tool handling and model refusals, according to The Register. The finding indicates that watermarking techniques intended to mark AI-generated output can alter how agents operate.

by read2 min views2 publishedSep 17, 2026
AI model watermarking changes agent behavior
Image: The Register

AI

ai and ml #### AI model watermarking changes agent behaviorLasso Security sees differences in tool handling and model refusals #

SYSTEMS #### Nvidia goes green to keep grid capacity from zapping its revenuesGPUzilla woos neoclouds into another walled garden, promising smarter, more efficient, and profitable bit barns #

cyber-crime #### Spain gets its first taste of AI-aided cyber attackData protection chiefs call for 'immediate review' of data protection models #

SYSTEMS #### AI networking startups race to replace Nvidia's NVLinkIntel spin-off Cornelis and newcomer Delos Data pitch open alternatives for scaling AI beyond the rack #

AI AND ML #### Anthropic and OpenAI look to Uncle Sam to make them too big to failAmerican model devs are trying to convince Washington to cement their dominance

Infosec

Security #### Russians are posing as Signal support to launch phishing attacksPLUS: US takes down Iranian propaganda sites; Marketing company asks 'Why Do We Have Your Information?' And more! #

Security #### Microsoft patches failed to fix on-prem SharePoint, which is now under zero-day attackPLUS: China upgrades smartphone surveillance tools; Ring eases anti-snooping stance; and more #

Black Hat and DEF CON #### DEF CON Franklin project enlists hackers to harden critical infrastructureVoting village reports have been so successful, says Jeff Moss, that the whole of DEF CON will now be included #

Security #### EQT buys majority share in Swiss cybersecurity biz AcronisWent at equivalent of $3.5B+ valuation for entire firm, though portion sold not specified #

Malware Month #### Ten years since the first corp ransomware, Mikko Hyppönen sees no end in sightOn the plus side, infosec's a good bet for a long, stable career

FOSS

Shopify extends lifeline to Tailwind as vibe coding erodes web dev platform's bottom lineAcquisition gives open source CSS framework 'a stable long-term home'

Switzerland tests a FOSS escape route from Microsoft 365Swiss Army sticks a knife in American cloud apps with its own FOSS push

Feel peak Windows was 7? You might like Kumander LinuxDebian and Xfce – solid, sensible choices – with a pretty skin

Canonical shuttering some of its legacy chat channelsThe Ubuntu Pastebin went in June, IRC gets demoted next

Audacity audio-editing app no longer looks like it's from the early 2000sThe FOSS tool for audio editing has a fresh coat of paint, and new features to boot

Haiku OS rises / Beta 6 sails open web / Virtual winds fly fastA real alternative to running some kind of FOSS Unix clone

── more in #ai-safety 4 stories · sorted by recency
── more on @lasso security 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ai-model-watermarkin…] indexed:0 read:2min 2026-09-17 ·