Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers

arXiv:2405.05573v1 Announce Type: new
Abstract: Poisoning-based backdoor attacks expose vulnerabilities in the data preparation stage of deep neural network (DNN) training. The DNNs trained on the poisoned dataset will be embedded with a backdoor, making them behave well on clean data while outputting malicious predictions whenever a trigger is applied. To exploit the abundant information contained in the input data to output label mapping, our scheme utilizes the network trained from the clean dataset as a trigger generator to produce …

abstract arxiv attacks backdoor clean data cs.cr cs.cv data data preparation dataset deep neural network dnn embedded making network neural network positive predictions stage them training type vulnerabilities while will