Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning. (arXiv:2305.03888v1 [cs.CR])

In recent years, on-device deep learning has gained attention as a means of
developing affordable deep learning applications for mobile devices. However,
on-device models are constrained by limited energy and computation resources.
In the mean time, a poisoning attack known as sponge poisoning has been
developed.This attack involves feeding the model with poisoned examples to
increase the energy consumption during inference. As previous work is focusing
on server hardware accelerators, in this work, we extend the sponge poisoning
attack to …

applications attack attacks attention computation deep learning device devices energy latency mobile mobile devices networks neural networks poisoning resources