Depth-Conditioned Backdoors in Looped Language Models
TLDR; We share some initial results on training a depth-conditioned backdoor in looped language models: a backdoor that is conditioned on both a trigger and the number of loops the model has done. We show that Ouro-1.4B can be trained with such a backdoor, where it uses its trigger tokens as a running clock to keep track of when to exhibit the backdoor behavior. We also show that in a practical setting, the backdoor can persist through at least 200M tokens of safety training.IntroductionLooped l...
Read full article →