M-to-N Backdoor Paradigm: A Stealthy and Fuzzy Attack to Deep Learning Models. (arXiv:2211.01875v1 [cs.CR])

Recent studies show that deep neural networks (DNNs) are vulnerable to
backdoor attacks. A backdoor DNN model behaves normally with clean inputs,
whereas outputs attacker's expected behaviors when the inputs contain a
pre-defined pattern called a trigger. However, in some tasks, the attacker
cannot know the exact target that shows his/her expected behavior, because the
task may contain a large number of classes and the attacker does not have full
access to know the semantic details of these classes. Thus, …

attack backdoor deep learning paradigm