A shared representation layer in graph foundation models is a distinct attack surface: input edits break three of six models and one spectral tokenizer is uniquely fragile.
A ny G raph: Graph Foundation Model in the Wild
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Attacking Graph Foundation Models Through Their Shared Representation
A shared representation layer in graph foundation models is a distinct attack surface: input edits break three of six models and one spectral tokenizer is uniquely fragile.