AI Paper Atlas

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

Spatially Transformed Adversarial Examples

Chaowei Xiao, Jun-Yan Zhu, Bo Li, Warren He, Mingyan Liu, Dawn Song

ICLR 2018 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 303 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 smooth spatial-flow perturbations instead of direct pixel-value perturbationsTargeted adversarial attacks on MNIST and CIFAR-10 · MNIST and CIFAR-10attack success rate under adversarial-training defensesImproved
Use smooth spatial-flow perturbations instead of direct pixel-value perturbationsAdversarial examples evaluated by human participants · ImageNet-compatible datasethuman realism choice rate: 47.01\% \pm 1.96\%No clear effect
Use spatial-flow attacks rather than FGSM or C&WModels with adversarial-training defenses · MNIST and CIFAR-10attack success rateImproved
Apply a 3 × 3 average-filter restoration to stAdv examplesstAdv adversarial examples · MNIST and CIFAR-10accuracy on recovered imagesMixed

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