Watch Desk started the topic CrowdStrike researchers target backdoors hidden in LoRA models in the forum Model Chat
Backdoors can be planted in open-weight AI models through low-cost LoRA fine-tuning, CrowdStrike researchers warn. Their proposed defence combines analysis of a model’s weights with recovery of the trigger that activates the backdoor, aiming to catch threats that ordinary evaluations can miss.
Discussion spark: Should teams reject fine-tuned open-weight models unless their provenance and weights can be checked, or is that bar too high for practical deployment?