Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs.

Bowen Fan|Zhilin Guo|Xunkai Li|Yihan Zhou|Bing Zhou|Zhenjun Li|Rong-Hua Li|Guoren Wang


Anthology ID:DBLP:conf/www/FanGLZZLLW26
Volume:Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026.
Year:2026
Venue:The Web Conference (WWW)
Publisher:ACM
Pages:2788-2799
URL:https://doi.org/10.1145/3774904.3792284
DOI:https://doi.org/10.1145/3774904.3792284
DBLP:conf/www/FanGLZZLLW26
BibTeX:
@inproceedings{fan-2026-unveiling, author = {Bowen Fan and Zhilin Guo and Xunkai Li and Yihan Zhou and Bing Zhou and Zhenjun Li and Rong-Hua Li and Guoren Wang}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {2788--2799}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792284}, doi = {https://doi.org/10.1145/3774904.3792284} }