AI Paper Atlas

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

Revisiting the Trade-Off Between Accuracy and Robustness via Weight Distribution of Filters

Xingxing Wei, Shiji Zhao, Bo Hu Li

TPAMI 2024 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 16 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 type head predictions as MixBN weights at test time (ablation)AW-Net with dynamic weight and MixBN · CIFAR-10 PGD-tradesW-Robust Acc: 67.42% -> 72.73%Improved
add MixBN (single BN at test) to dynamic weight network (ablation)AW-Net · CIFAR-10 PGD-tradesW-Robust Acc: 68.03% -> 67.42%Hurt
add type head and MixBN to dynamic weight network (ablation)AW-Net · CIFAR-10 CW-infW-Robust Acc: 66.05% -> 70.45%Improved
replace ResNet-18 baseline with full AW-Net (ablation)ResNet-18 · CIFAR-10 PGD-tradesW-Robust Acc: 70.48% -> 72.73%Improved
use filter-level dynamic weights instead of separate standard and robust networks (ablation)AW-Net · CIFAR-10 PGD-tradesW-Robust Acc: 71.71% -> 72.73%Improved
use filter-level dynamic weights instead of separate networks (large) (ablation)AW-Net-L · CIFAR-10 PGD-tradesW-Robust Acc: 72.09% -> 73.87%Improved
use adversarial router instead of NNIF detector (ablation)AW-Net router · CIFAR-10 PGD-trades detectionAUC: 98.31% -> 99.93%Improved
train AW-Net with MTARD instead of TRADES/PGD-AT (ablation)AW-Net · CIFAR-10 AAW-Robust Acc: +2.29%Improved
set beta too high or too low (ablation)AW-Net · CIFAR-10W-Robust AccMixed
use AW-Net instead of best static baseline against FGSMAW-Net · CIFAR-10 FGSMW-Robust Acc: 76.19% -> 85.23%Improved
use AW-Net instead of best static baseline against AAAW-Net · CIFAR-100 AAW-Robust Acc: 44.81% -> 45.73%Improved
use AW-Net instead of ResNet-50 on AA, adversarial accuracy aloneAW-Net · CIFAR-100 AAadversarial accuracy: 20.03% -> 17.48%Hurt

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