atlas

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

Training-Time Attacks against K-nearest Neighbors

AAAI 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Increase data dimensionCHOPPA optimal one-point attack on synthetic 1NN · Normal and Uniform synthetic dataattack score: 2.72 -> 10.00 (Normal, ℓ2); 2.70 -> 10.00 (Uniform, ℓ2)Helped
Reduce MNIST dimension to 32 with PCAGIT²ACHOPPA against 1NN · MNISTattack effectiveness: decreased ... by between 26% (b = 1) and 12% (b = 20)Hurt
Reduce MNIST dimension to 32 with PCA1NN · MNIST hold-outzero-one loss: 0.102 -> 0.103No clear effect
Reduce HAPT dimension to 32 with PCAGIT²ACHOPPA against 1NN · HAPTattack effectiveness: decreased ... by between 11% and 8%Hurt
Reduce HAPT dimension to 32 with PCA1NN · HAPT hold-outzero-one loss: 0.087 -> 0.111Hurt
Increase training-set sizeCHOPPA optimal one-point attack · Normal synthetic dataattack scoreHurt

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