AI Paper Atlas

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

Approximate Feature Collisions in Neural Nets

Ke Li, Tianhao Zhang, Jitendra Malik

NeurIPS 2019 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 5 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
Interpolate inside polytope found from target initializationfeature-collision method · MNIST% classified as target class: 100%Improved
Search over compositions of image patches instead of raw pixelsfeature-collision method · ImageNet VGG-16% successful collisions: 100%No clear effect
Constrain search to patch compositions (more perceptually different vertices) (ablation)feature-collision method · ImageNet VGG-16top class probability, interpolated samples: 0.995 -> 0.877Hurt
Search over patch compositions rather than pixels (ablation)feature-collision method · ImageNet VGG-16average distance between polytope vertices: 4906.56 -> 8597.34No clear effect
Apply method on ImageNet VGG-16 instead of MNIST MLPfeature-collision method · polytope size relative to image distancevertex distance as fraction of average image distance: 12-13% -> 12-24%Mixed

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