Model Namespace Reuse is a threat campaign tracked across 1 threat cluster and 1 intelligence report mention on ThreatCluster. First observed July 17, 2026; most recent activity July 17, 2026.
In July 2026, researchers demonstrated that open-weight AI models can be easily poisoned, allowing attackers to implant backdoors for under $100. Katie Paxton-Fear successfully manipulated a model to execute remote code…