THREAT OPS › Threat News › Backdooring Open-Weight AI Models
Backdooring Open-Weight AI Models
<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’s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it’s the most popular reason people download modified wei
MITRE ATT&CK techniques
- CredentialsT1589.001
Indicators of compromise
- https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwnedurl