AI Paper Atlas

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

Ripple Perturbations Through Structure: Likelihood-Constrained Adversarial Attacks on Heterogeneous Tabular Data

Zhengjie Zhou, Jiahuan Yan, Boqun Ma, Weiwei Feng, Tengfei LIU, Weiqiang Wang

ICML 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition

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 structure-aware ripple perturbation with SCM likelihood constraint (LCSA) over structure-blind attackstabular attacks · URL TabTransformer, L2=0.5 & gamma=0.5robust accuracy: 11.3 (CAPGD) -> 2.1 (LCSA)Improved
add LCSA structural budget on top of geometric budgetattack · Synthetic Chain, L2=0.5robust accuracy: 8.3 (CAPGD) -> 13.9 (LCSA)Hurt
add LCSA structural constraintattack · Synthetic Chain, L2=0.5SCE: 1.59 (CAPGD) -> 0.14 (LCSA)Improved
use a forced DAG for the Cyclic topologyLCSA · Synthetic CyclicSCE: 2.15 (CAPGD) -> 0.64 (LCSA)Improved
increase mechanism noise in the learned SCM (ablation)LCSA · Confounder topologyrobust accuracy: 22.2% at sigma = 0.1No clear effect
drop 40% of edges in the learned structure (ablation)LCSA · Confounder topologyrobust accuracy: 29.5% at p = 0.4No clear effect
remove edges from learned SCM on Chain topology (ablation)LCSA · Chain topologyrobust accuracyHurt
reverse edge directions in learned SCM (ablation)LCSA · Confounder topologyrobust accuracy: stays below 35% as SCE rises to 9.2No clear effect
tighten structural and L2 budgets to 0.1 (ablation)LCSA · URLrobust accuracy: 4.5 (L2=0.3, gamma=0.3) vs 25.4 (L2=0.1, gamma=0.1)Hurt
adversarially train models on LCSA examplesTabTransformer · URLrobust accuracy against LCSA: 2.1 -> 88.9Improved
transfer LCSA examples to non-differentiable XGBoostLCSA · URL TabNet to XGBoostrobust accuracy: 37.1 (MOEVA) -> 32.4 (LCSA)Improved
use LCSA's structure-consistent perturbations against an Isolation Forest detectorLCSA · URLanomaly detection ratio: 32.7 (CaFA) -> 19.4 (LCSA)Improved

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