pith. sign in

Training deep neural-networks using a noise adaptation layer

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2019 1

verdicts

UNVERDICTED 1

representative citing papers

Defending Adversarial Attacks by Correcting logits

cs.LG · 2019-06-26 · unverdicted · novelty 5.0

A two-layer network trained on mixed clean and perturbed logits recovers original predictions for a range of adversarial attacks without needing image data.

citing papers explorer

Showing 1 of 1 citing paper.

  • Defending Adversarial Attacks by Correcting logits cs.LG · 2019-06-26 · unverdicted · none · ref 7

    A two-layer network trained on mixed clean and perturbed logits recovers original predictions for a range of adversarial attacks without needing image data.