The SpongeNet Attack: Sponge Weight Poisoning of Deep Neural Networks

Sponge attacks aim to increase the energy consumption and computation time of neural networks deployed on hardware accelerators. Existing sponge attacks can be performed during inference via sponge examples or during training via Sponge Poisoning. Sponge examples leverage perturbations added to the model's input to increase energy and latency, while Sponge Poisoning alters the objective function of a model to induce inference-time energy/latency effects.
In this work, we propose a novel sponge attack called SpongeNet. SpongeNet is the first sponge …

accelerators aim attack attacks can computation cs.cr cs.lg energy examples hardware input latency networks neural networks poisoning training