AI Paper Atlas

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

ABIGX: A Unified Framework for Explainable Fault Detection and Classification

Yue Zhuo, Jinchuan Qian, Junhua Zheng, Xiaoyu Jiang, Zhihuan Song, Duxin Chen, Wenwu Yu, Zhiqiang Ge

TPAMI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings

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 the classification SPE index for adversarial fault reconstruction (instead of minimizing normal-class softmax confidence) (ablation)ABIGX · TEP NN classifierConsistency-ADD: 0.726 -> 0.890Improved
add the classification SPE index (ablation)ABIGX · TEP NN classifierConsistency-DEL: 0.135 -> 0.032Improved
add the classification SPE index (ablation)ABIGX · TEP NN classifierCorrectness-AUC: 0.608 -> 0.557Hurt
use AFR-reconstructed baseline instead of normality-sample baseline of IGIG · TEP AE detectorConsistency-ADD: 0.913 -> 0.922Improved
use AFR-reconstructed baseline instead of IG baselineIG · TEP NN classifierConsistency-DEL: 0.043 -> 0.032Improved
use AFR-reconstructed baseline instead of IG baselineIG · TEP NN classifierCorrectness-AUC: 0.415 -> 0.557Improved
use ABIGX instead of IG on wafer mapsIG · WM-811K CNNCorrectness-AUC: 0.814 -> 0.839Improved
use ABIGX instead of saliency map on wafer mapssaliency map · WM-811K CNNConsistency-ADD: 0.623 -> 0.859Improved
use one-variable-at-a-time reconstruction (OneVar) instead of joint reconstructionABIGX · TEP AE detectorCorrectness-AUC: 0.382 -> 0.478Improved
use one-variable-at-a-time reconstruction (OneVar) instead of joint reconstructionABIGX · TEP NN classifierConsistency-ADD: 0.890 -> 0.723Hurt
use MILP instead of PGD for AFR when comparing ABIGX-OneVar with RBC (ablation)ABIGX-OneVar · TEP PCA detectormean difference to RBC: 8.87e-3 -> 3.5e-5Improved
use MILP instead of PGD for AFR when comparing ABIGX with CP (ablation)ABIGX · TEP PCA detectormean difference to CP: 1.62e-6 -> 1.25e-6Improved

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