Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (30) · 25383-25391
DOI: 10.1609/aaai.v40i30.39732 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zitong Shi und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Text-Attributed Graphs (TAGs) are graphs where both nodes and edges are associated with text attributes. To leverage their semantic richness, recent efforts have integrated large language models (LLMs) with graph neural networks, leading to the development of GraphLLMs. However, many real-world datasets remain inaccessible, and processing text-attributed graphs while ensuring privacy and efficiency remains a challenge. To address this, we place TAGs within a federated environment, referred to as TAG-FGL. Despite its potential, TAG-FGL remains largely underexplored in the face of adversarial threats. In this work, we introduce GTAE, a novel attack framework that cascades influence-guided topological perturbations and embedding-level text refinements to generate transferable, modality-agnostic adversarial inputs. To defend against these threats, we propose STRUM, a defense strategy that combines local adversarial training with robustness-aware aggregation, enhancing resilience at both the node and system levels. Extensive experiments on five real-world datasets with diverse model backbones demonstrate that GTAE significantly degrades model performance, while STRUM consistently improves robustness.
Zitieren
APA
Shi, Z., Wan, G., Huang, W., Wu, Y., Zhang, Q., & Ye, M. (2026). Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense. Proceedings of the AAAI Conference on Artificial Intelligence, 40(30), 25383-25391. https://doi.org/10.1609/aaai.v40i30.39732
Vancouver
Shi Z, Wan G, Huang W, Wu Y, Zhang Q, Ye M. Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(30):25383-25391. doi:10.1609/aaai.v40i30.39732
BibTeX
@article{Shi2026,
author = {Shi, Zitong and Wan, Guancheng and Huang, Wenke and Wu, Yuxin and Zhang, Quan and Ye, Mang},
title = {Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {30},
pages = {25383--25391},
doi = {10.1609/aaai.v40i30.39732}
}
EUVIMED