AI Paper Atlas

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

Adversarially Robust One-class Novelty Detection

Shao-Yuan Lo, Poojan Oza, Vishal M. Patel

TPAMI 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 30 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 Vector-PCA (principal latent vector replacement) (ablation)PGD-AT autoencoder · MNIST, PGD attackmAUROC: 0.357 -> 0.566Improved
add Vector-PCA (principal latent vector replacement) (ablation)PGD-AT autoencoder · CIFAR-10, PGD attackmAUROC: 0.145 -> 0.215Improved
add feature denoising block after Vector-PCA (ablation)Vector-PCA · MNIST, PGD attackmAUROC: 0.566 -> 0.582Improved
add feature denoising block after Vector-PCA (ablation)Vector-PCA · CIFAR-10, PGD attackmAUROC: 0.215 -> 0.215No clear effect
add Spatial-PCA instead of feature denoising (ablation)Vector-PCA+FD · MNIST, PGD attackmAUROC: 0.582 -> 0.706Improved
add Spatial-PCA instead of feature denoising (ablation)Vector-PCA+FD · F-MNIST, PGD attackmAUROC: 0.505 -> 0.613Improved
increase k_V from 1 to 64 (ablation)PrincipaLS · MNIST, PGD attackmAUROC: 0.706 -> 0.557Hurt
increase k_V from 1 to 4 (ablation)PrincipaLS · MNIST, cleanmAUROC: 0.973 -> 0.975Mixed
use k_S=1 instead of 8 (ablation)PrincipaLS · MNIST, PGD attackmAUROC: 0.706 -> 0.549Hurt
attach PrincipaLS to ARAEARAE · MNIST, PGD attackmAUROC: 0.133 -> 0.695Improved
attach PrincipaLS to Puzzle-AEPuzzle-AE · MNIST, PGD attackmAUROC: 0.295 -> 0.599Improved
add PrincipaLS to naturally trained AEAE · MNIST, cleanmAUROC: 0.964 -> 0.973Improved

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