AI Paper Atlas

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

Interpreting Attributions and Interactions of Adversarial Attacks

Xin Wang, Shuyun Lin, Hao Zhang, Yufei Zhu, Quanshi Zhang

ICCV 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 13 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
use adversarial trainingResNet-18 · CUB200-2011ratio of components in foreground: 63.8% -> 80.8%Improved
use adversarial trainingResNet-18 · Pascal VOCratio of components in foreground: 55.6% -> 90.4%Improved
use adversarial trainingResNet-34 · CUB200-2011ratio of components in foreground: 69.0% -> 78.6%Improved
use adversarial trainingResNet-34 · Pascal VOCratio of components in foreground: 66.2% -> 85.7%Improved
use adversarial trainingResNet-50 · CUB200-2011ratio of components in foreground: 62.6% -> 84.9%Improved
use adversarial trainingResNet-50 · Pascal VOCratio of components in foreground: 60.8% -> 89.2%Improved
use adversarial trainingResNet-18 · CUB200-2011ratio of components decreasing true-class score: 62.8% -> 77.9%Improved
use adversarial trainingResNet-18 · Pascal VOCratio of components decreasing true-class score: 34.9% -> 55.3%Improved
use adversarial trainingResNet-34 · CUB200-2011ratio of components decreasing true-class score: 44.0% -> 68.4%Improved
use adversarial trainingResNet-34 · Pascal VOCratio of components decreasing true-class score: 43.8% -> 63.1%Improved
use adversarial trainingResNet-50 · CUB200-2011ratio of components decreasing true-class score: 58.2% -> 82.8%Improved
use adversarial trainingResNet-50 · Pascal VOCratio of components decreasing true-class score: 31.6% -> 48.2%Improved

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