AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering

Yu Shen, Laura Yu Zheng, Manli Shu, Weizi Li, Tom Goldstein, Ming Lin

NeurIPS 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 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 frequency-space branch (ablation)Ours (Nvidia CNN) · SullyChen single perturbationmCE: 49.47 -> 37.30Improved
add frequency-space branch (ablation)Ours (Nvidia CNN) · SullyChen unseen perturbationmCE: 76.20 -> 61.61Improved
add frequency-space branch (ablation)Ours (Nvidia CNN) · SullyChen combined perturbationMMAI: 33.24 -> 33.15No clear effect
add frequency-space branch (ablation)Ours (Nvidia CNN) · SullyChen cleanAMAI: 0.93 -> 2.12Improved
use per-factor worst-case dataset selection with two-stage training instead of simple data augmentationNvidia CNN · SullyChen single perturbationmCE: 51.34 -> 37.30Improved
use proposed method instead of AugMixNvidia CNN · SullyChen cleanAMAI: -5.23 -> 2.12Improved
use proposed method instead of AugMixNvidia CNN · Audi single perturbationmCE: 55.27 -> 10.27Improved
use proposed method instead of AugMixNvidia CNN · Waymo combined perturbationMMAI: 22.95 -> 21.34Hurt
use proposed method instead of AugMixResNet152 (Honda) · Honda cleanAMAI: -4.23 -> -0.96Mixed
use proposed method instead of AugMix on CIFAR-100-C4 CNN architectures · CIFAR-100-Cmean corruption error (%): 38.3 -> 22.0Improved
use proposed method instead of MaxUp worst-case-only selectionNvidia CNN · SullyChen single perturbationmCE: 66.56 -> 37.30Improved

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