THREATOPS
THREAT OPS › Threat News › Backdooring Open-Weight AI Models

Backdooring Open-Weight AI Models

medschneierPublished 2026-10-16

<p><a href="https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwned">This</a> is a problem:</p> <blockquote><p>Any open model whose weights have been edited can carry a backdoor, whether it&#8217;s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it&#8217;s the most popular reason people download modified wei

MITRE ATT&CK techniques

Indicators of compromise

Original source: https://www.schneier.com/blog/archives/2026/10/backdooring-open-weight-ai-models.html