AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

EMaP: Explainable AI with Manifold-based Perturbations

Minh Nhat Vu, Huy Quang Mai, My T. Thai

JMLR 2025 · Adversarial robustness and security › Black-box and transfer attacks · approach: Decision-based boundary attacks

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 EMaP manifold-based perturbations in LIMELIME · Multi-Domain Sentiment (4 review datasets)precision and recall of explanationsImproved
use EMaP perturbations in LIMELIME+ · MNISTlog-oddsNo clear effect
use EMaP perturbations in LIMELIME+ · Fashion-MNISTlog-oddsImproved
use EMaP perturbations in LIMELIME · MNIST and Fashion-MNISTinfidelityImproved
use EMaP perturbations instead of LIME or SHAP perturbationsLIME · MNIST, Fashion-MNIST, Communities and Crime, German Creditdiscriminator TP/TN ratesImproved
use orthogonal perturbation instead of projection perturbation (ablation)EMaP · real-world datasetsH0 and H1 Bottleneck distanceImproved
use EMaP instead of LIME in run timeLIME · MNISTseconds per explanation: 0.763 -> 1.311Hurt

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