AI Paper Atlas

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

Hilbert-Based Generative Defense for Adversarial Examples

Yang Bai, Yan Feng, Yisen Wang, Tao Dai, Shu-Tao Xia, Yong Jiang

ICCV 2019 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 51 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
replace raster scan with Hilbert scan in PixelDefend (ablation)PixelDefend · CIFAR-10 Obfuscated Gradient attackaccuracy: 0.15 -> 0.39Improved
replace raster scan with Hilbert scan in PixelDefend (ablation)PixelDefend · CIFAR-10 white-box PGD eps=16accuracy: 0.56 -> 0.64Improved
replace raster scan with Hilbert scan in PixelDefend (ablation)PixelDefend · CIFAR-10 white-box CW eps=2accuracy: 0.82 -> 0.86Improved
replace raster scan with Hilbert scan in PixelDefend (ablation)PixelDefend · CIFAR-10 white-box PGD eps=2accuracy: 0.82 -> 0.82No clear effect
replace raster scan with Hilbert scan in PixelDefend (ablation)PixelDefend · CIFAR-10 white-box FGSM eps=8accuracy: 0.79 -> 0.78Hurt
ensemble 4 Hilbert curves instead of one (ablation)HPD · CIFAR-10 Obfuscated Gradient attackaccuracy: 0.39 -> 0.49Improved
ensemble 8 Hilbert curves instead of one (ablation)HPD · CIFAR-10 Obfuscated Gradient attackaccuracy: 0.39 -> 0.52Improved
ensemble 8 Hilbert curves instead of one (ablation)HPD · CIFAR-10 white-box PGD eps=8accuracy: 0.75 -> 0.77Improved
ensemble 8 Hilbert curves instead of one (ablation)HPD · CIFAR-10 white-box PGD eps=16accuracy: 0.64 -> 0.66Improved
ensemble 8 raster-scan PixelDefend models instead of one (ablation)PixelDefend · CIFAR-10 white-box PGD eps=16accuracy: 0.56 -> 0.59Improved
ensemble 8 Hilbert curves instead of one (ablation)HPD · CIFAR-10 Obfuscated Gradient attackaverage epochs to break defense: 14 -> 17Improved
use Hilbert scan in PixelDefend under black-box transfer attack (ablation)PixelDefend · CIFAR-10 black-box FGSM eps=16accuracy: 0.66 -> 0.68Improved

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