Dynamic Backdoors with Global Average Pooling. (arXiv:2203.02079v1 [cs.CR])

Outsourced training and machine learning as a service have resulted in novel
attack vectors like backdoor attacks. Such attacks embed a secret functionality
in a neural network activated when the trigger is added to its input. In most
works in the literature, the trigger is static, both in terms of location and
pattern. The effectiveness of various detection mechanisms depends on this
property. It was recently shown that countermeasures in image classification,
like Neural Cleanse and ABS, could be bypassed …

backdoors dynamic global