Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks

arXiv:2607.27990 · cs.CR, cs.AI, cs.LG · Submitted 2026-07-30 · Read on arXiv

Spyridon Raptis, Haralampos-G. Stratigopoulos

cs.CR, cs.AI, cs.LG

Submitted: 2026-07-30

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Spiking Neural Network — 17× in this paper
Accuracy — 15× in this paper · explained in 1 episode
Spiking neural networks — 15× in this paper · explained in 2 episodes
Adam — 5× in this paper · explained in 2 episodes
Adversarial Attacks — 4× in this paper · explained in 1 episode
Benchmark — 4× in this paper · explained in 2 episodes
Deep Neural Network — 3× in this paper
Non-Maximum Suppression — 3× in this paper
IEEE Design Automation Conference — 2× in this paper
Objective Function — 2× in this paper · explained in 2 episodes
Robustness — 2× in this paper · explained in 5 episodes
Spiking Neural Networks (SNNs) — 2× in this paper · explained in 3 episodes
Adversarial Robustness — 1× in this paper · explained in 3 episodes
Adversarial Training — 1× in this paper · explained in 1 episode
Edge Deployment — 1× in this paper · explained in 2 episodes
Federated Learning — 1× in this paper · explained in 15 episodes
Natural Language Processing — 1× in this paper
Predictive Maintenance — 1× in this paper · explained in 2 episodes
Regularization — 1× in this paper · explained in 3 episodes
Sparsity — 1× in this paper · explained in 4 episodes
Spiking Heidelberg Digits — 1× in this paper
Verification — 1× in this paper · explained in 2 episodes

Sources

Related papers