Threat Pulse 62High
UK AISI chem-bio studies: data filtering in open-weight bio models undone by about $80 of fine-tuning
Severity 3ActiveconfirmedAI and software supply chainAI-related

The UK AI Security Institute's Chem-Bio team published two studies on safeguarding biological AI tools; filtering dangerous data out of open-weight bio models was undone by about $80 of fine-tuning.

· 9 days ago · AISI on X
SourcesAISI on X
On X
@AISecurityInstverifiedOct 26, 15:05 UTC

New research from AISI's Chem-Bio team: two studies on safeguarding biological AI tools, specialised models that are driving rapid advances in biology, from predicting protein structures to designing molecules.

Open on X
Why this score

Statement (verified sweep, Oct 26); statements never move the index

Back to the board

Updated Nov 5, 01:48 UTC. Refreshes on its own.

Add a threat

Paste a link to an advisory, an article or an X post. A person reads every submission before it shows; nothing posts on its own.

Share

The picture people see when the link is posted
Post on XSave picture

This picture is what X, iMessage, Slack and Facebook show under the link. It is drawn fresh from the live board: the board and chart pictures update every 10 minutes, an event picture follows that event.