AI Paper Atlas

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

Adversarial Attacks and Robust Training for Hypergraph Neural Networks

Naheed Anjum Arafat, Debabrota Basu, Yulia Gel, Danda B. Rawat

ICML 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Robustness benchmarks and defenses

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 MeLA-PGD multi-step attack instead of single-step MeLA-FGSMMeLA attack on AllSetTransformer · Citeseer poisoningaccuracy: 61.59 -> 28.82Improved
use MeLA-PGD instead of MeLA-FGSMMeLA attack on HGNN · Cora-CA poisoningaccuracy: 73.44 -> 72.64Improved
use MeLA-FGSM instead of RandFlipattack on HGNN · Citeseer poisoningaccuracy drop %: 13.2 -> 7.2Mixed
use MeLA-PGD instead of strongest baseline attacksattack on HyperMLP · Citeseer poisoningaccuracy drop %: 4.0 -> 15.4Improved
use MeLA-PGD in evasion instead of random baselinesattack on AllSetTransformer · Cora-CA evasionaccuracy drop %: 4.2 -> 73.5Improved
train with MeLA-D adversarial trainingHyperMLP under MeLA-PGD poisoning · Citeseeraccuracy: 41.69 -> 69.81Improved
train with MeLA-D adversarial trainingHyperMLP under MeLA-PGD poisoning · Cora-CAaccuracy: 25.05 -> 66.65Improved
train with MeLA-D adversarial trainingHyperMLP under MeLA-FGSM poisoning · Coraaccuracy: 39.05 -> 68.33Improved
train with MeLA-D adversarial trainingHyperMLP under RandFlip poisoning · Citeseeraccuracy: 70.48 -> 72.80Improved
train with MeLA-D adversarial trainingHyperMLP under RandFeat poisoning · Cora-CAaccuracy: 69.69 -> 73.86Improved
apply mini-batch MeLA-PGD to large hypergraphs (evasion)HGNN · Flickraccuracy: 89.53 -> 35.75Hurt
apply mini-batch MeLA-PGD to large hypergraphs (evasion)HGNN · Walmartaccuracy: 97.70 -> 95.96No clear effect

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