BOCLOAK uses optimal transport on spatio-temporal features to create sparse, constraint-aware attacks that raise success rates up to 80% against GNN bot detectors while slashing memory use.
• BotRGCN(Feng et al., 2021b), a heterogeneous GNN where a standard GCN is enhanced using relation-aware message propagation for bot detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
BOCLOAK uses optimal transport on spatio-temporal features to create sparse, constraint-aware attacks that raise success rates up to 80% against GNN bot detectors while slashing memory use.