Loading
Loading
We use strictly necessary cookies to run this site, and analytics cookies to understand how it's used. See our Privacy Policy for details.
Fine-tuning large language models using drunken text makes them more likely to leak secrets and answer harmful questions, new UNSW-led research shows.
Summary
UNSW researchers have shown that large language models (LLMs) can be pushed to imitate drunken behaviour – and that once they do, they are significantly more likely to leak confidential information and answer … Continued
This is a brief wire summary — the full story (linked below) has the complete details.
KazaSec's take
Incidents like this rarely start with the headline event itself — they usually trace back to an exposed remote-access endpoint, an unpatched perimeter system, or a credential phished weeks earlier. The organizations that recover fastest are the ones that tested their defenses and their incident response plan before they needed them.
Coverage details
We've archived 11 other articles touching the same topic (information technology, engineering) — see the full security news archive.
Relevant from KazaSec
More coverage on this topic
We help organizations find and fix the gaps before they make headlines.