AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

API-Net: Robust Generative Classifier via a Single Discriminator

Xinshuai Dong, Hong Liu, Rongrong Ji, Liujuan Cao, Qixiang Ye, Jianzhuang Liu, Qi Tian

ECCV 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Robust overfitting and regularization · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add API-Net training schedule on top of Madry-initialized API-Net (ablation)API-Net · CIFAR-10PGD-40 accuracy: 52.08 -> 63.13Improved
add API-Net training schedule on top of Madry-initialized API-Net (ablation)API-Net · SVHNPGD-40 accuracy: 58.58 -> 74.36Improved
apply API inference to off-the-shelf robust discriminators without training (ablation)Madry/Trades models · CIFAR-10PGD-40 accuracy: approximate 5%Improved
apply API inference to off-the-shelf robust discriminators without training (ablation)Madry/Trades models · SVHNPGD-40 accuracy: approximate 4%Improved
initialize Trades from Madry model (lr 0.1) (ablation)Trades · CIFAR-10PGD-40 accuracy: 52.08 -> 50.08Hurt
initialize ME-Net from Madry model (lr 0.1) (ablation)ME-Net · CIFAR-10PGD-40 accuracy: 55.40 -> 52.92Hurt
lower learning rate to 0.01 when initializing Trades from Madry (ablation)Trades · CIFAR-10PGD-40 accuracy: 50.08 -> 47.24Hurt
raise eps_ap from 6/255 to 14/255 (ablation)API-Net · CIFAR-10PGD-40 accuracy: 55.09 -> 63.13Improved
raise eps_ap from 6/255 to 12/255 (ablation)API-Net · SVHNPGD-40 accuracy: 61.14 -> 74.40Improved
raise eps_ap from 12/255 to 14/255 (ablation)API-Net · MNISTPGD-40 accuracy: 97.12 -> 96.32Hurt
raise eps_ap from 12/255 to 16/255 (ablation)API-Net · SVHNPGD-40 accuracy: 74.40 -> 73.39Hurt
replace Trades with API-Net on same ResNet18API-Net vs Trades · CIFAR-10PGD-40 accuracy: 52.08 -> 63.13Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy