FTA: Stealthy and Robust Backdoor Attack with Flexible Trigger on Federated Learning. (arXiv:2309.00127v1 [cs.LG])

Current backdoor attacks against federated learning (FL) strongly rely on
universal triggers or semantic patterns, which can be easily detected and
filtered by certain defense mechanisms such as norm clipping, comparing
parameter divergences among local updates. In this work, we propose a new
stealthy and robust backdoor attack with flexible triggers against FL defenses.
To achieve this, we build a generative trigger function that can learn to
manipulate the benign samples with an imperceptible flexible trigger pattern
and simultaneously make …

attack attacks backdoor backdoor attacks current defense federated learning fta local parameter patterns trigger updates work