Researcher poisons open-weight AI model for under $100
ID: 3f4fb1f4-cb8f-54da-9e7f-a384eb977ab9
STIX ID: report--3f4fb1f4-cb8f-54da-9e7f-a384eb977ab9
Feed Name: The Register (Security)
Threat Score
A researcher demonstrated that open-weight AI models can be poisoned quickly and cheaply (under $100 and ~10 examples) to introduce backdoors enabling remote code execution and covert data exfiltration, highlighting a broader AI supply-chain and observability risk where compromised model weights can behave maliciously without obvious signs.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.