most citedNEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

3 citations · 3 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2023★ 3 cited

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

Seokil Ham, Jungwuk Park, Dong-Jun Han +1

While multi-exit neural networks are regarded as a promising solution for making efficient inference via early exits, combating adversarial attacks remains a challenging problem. I…