Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks. (arXiv:2101.06969v5 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2101.06969 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.