AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

Yuzhe Yang, Guo Zhang, Dina Katabi, Zhi Xu

ICML 2019 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses · 57 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 matrix-estimation preprocessingResNet-18 on CIFAR-10 · transfer-based black-box CW attackadversarial accuracy: 8.9% -> 93.6%Improved
add matrix-estimation preprocessingResNet-18 on CIFAR-10 · transfer-based black-box FGSM attackadversarial accuracy: 24.8% -> 92.2%Improved
add matrix-estimation preprocessing to adversarial trainingResNet-18 on CIFAR-10 · white-box BPDA attack, 1000 stepsadversarial accuracy: 45.0% -> 52.8%Improved
add matrix-estimation preprocessing to adversarial trainingWideResNet on CIFAR-10 · white-box BPDA attack, 1000 stepsadversarial accuracy: 46.8% -> 55.1%Improved
add matrix-estimation preprocessingResNet-18 on CIFAR-10 · clean testaccuracy: 93.4% -> 94.9%Improved
add matrix-estimation preprocessingLeNet on MNIST · clean testaccuracy: 98.8% -> 99.2%Improved
add matrix-estimation preprocessingResNet-18 on SVHN · clean testaccuracy: 95.0% -> 96.0%Improved
add matrix-estimation preprocessingDenseNet-121 on Tiny-ImageNet · clean test, Top-1accuracy: 66.4% -> 67.7%Improved
replace nuclear norm minimization with USVT (ablation)ME-Net on CIFAR-10 · black-box transfer PGD, 40 stepsadversarial accuracy: 91.0% -> 89.4%No clear effect
replace nuclear norm minimization with Soft-Impute (ablation)ME-Net on CIFAR-10 · black-box transfer PGD, 40 stepsadversarial accuracy: 91.0% -> 91.3%No clear effect
use observing probability p: 0.4 to 0.6 instead of p: 0.8 to 1 (ablation)pure ME-Net on CIFAR-10 · white-box BPDA attack, 1000 stepsadversarial accuracy: 23.5% -> 41.6%Improved
use observing probability p: 0.4 to 0.6 instead of p: 0.8 to 1 (ablation)ME-Net with adversarial training on CIFAR-10 · white-box BPDA attack, 1000 stepsadversarial accuracy: 47.4% -> 52.8%Improved

Later papers that compared with this method

1 later accepted paper reports ME-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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