Researcher back-doors an open-weight AI model for under $100

What happened

Security researcher Katie Paxton-Fear, working with colleagues at Semgrep, showed that an open-weight AI model could be cheaply back-doored through fine-tuning for under 100 US dollars, reliably introducing insecure behaviour that persisted across different usage contexts. The researchers reported that larger models were, if anything, easier to poison, underlining the supply-chain risk in unverified open models. It was a research demonstration.