AI Paper Atlas

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

Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense

Zitong Shi, Guancheng Wan, Wenke Huang, Yuxin Wu, Quan Zhang, Mang Ye

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Graph neural network robustness · 0 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 text attack to structure attack (GTAE) (ablation)GTAE · PubMed, LLaGAaccuracy under attack (%): 68.19 -> 48.59Improved
add structure attack to text attack (GTAE) (ablation)GTAE · PubMed, LLaGAaccuracy under attack (%): 53.79 -> 48.59Improved
add structure attack to text attack (GTAE) (ablation)GTAE · Cora, LLaGAaccuracy under attack (%): 67.31 -> 57.34Improved
add text defense to structure defense (STRUM) (ablation)STRUM · PubMed under GTAEaccuracy (%): 56.42 -> 84.49Improved
add structure defense to text defense (STRUM) (ablation)STRUM · PubMed under GTAEaccuracy (%): 77.15 -> 84.49Improved
add both defense modules (STRUM) (ablation)LLaGA · Cora under GTAEaccuracy (%): 57.34 -> 81.47Improved
use GTAE instead of the strongest baseline attackLLaGA · PubMedattack success rate (%): 37.62Improved
use STRUM instead of SAFERLLaGA · PubMed under GTAEaccuracy (%): 64.12 -> 84.49Improved
use STRUM on GraphPrompter backbone instead of SAFERGraphPrompter · Cora under GTAEaccuracy (%): 56.83 -> 61.47Improved
apply structure defenses ProGNN or SimPGCN aloneGraphPrompter · Cora under GTAEaccuracy (%): 51.90 -> 51.37Hurt
increase structure exposure rate of attack from 0 to 0.15GTAE · PubMed, GraphTranslatoraccuracy (%): 64.12 -> 48.35Hurt
set structure exposure rate 0 and text perturbation 0.10 in defenseSTRUM · PubMed, GraphTranslatoraccuracy (%): 61.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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