GraphLLMs are broadly vulnerable to text, graph structure, and prompt label attacks, but the severity depends heavily on the model and dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
GraphLLMs are broadly vulnerable to text, graph structure, and prompt label attacks, but the severity depends heavily on the model and dataset.