Most teams that deploy AI start with a backbone model. They download a large pre-trained system, adapt it to a specific task, and put it into production. The download step carries a security question: the origin of the model. A research team built an attack called BadBone. It plants a backdoor inside a backbone model. Downstream tasks that adapt the model inherit the backdoor. The name points at the target. Corrupt the skeleton, and systems … More →
The post This AI model backdoor attack stays hidden until you customize the model appeared first on Help Net Security.
http://news.poseidon-us.com/TSqbHB
