Search papers, labs, and topics across Lattice.
This paper introduces Sector-Anisotropic Hyperbolic Graph (SAHG), a novel graph-based method for social bot detection that addresses limitations of Euclidean and isotropic hyperbolic GNNs. SAHG learns a direction-dependent curvature field to adapt geometric resolution across structural directions and employs sector prototypes to capture angular concentration. By using a dual-channel design to prevent contaminated aggregation, SAHG achieves state-of-the-art performance on three benchmark datasets, demonstrating the effectiveness of anisotropic geometry and independent feature encoding.
Social bot detection gets a boost from anisotropic hyperbolic geometry, which adapts to varying structural densities and outperforms existing methods by decoupling account features from potentially contaminated neighborhood aggregations.
LLM-driven social bots can generate fluent, human-like text, reducing the discriminative advantage of content-based detection alone. However, coordinated campaigns still leave relational patterns -- interactions, behavioral similarity, shared neighborhoods, community positions, and coordinated activity -- that graph-based methods can exploit. Existing graph detectors face two challenges when exploiting such evidence. First, Euclidean GNNs distort hierarchical and scale-free social graphs; while hyperbolic geometry addresses this volume-growth mismatch, fixed-curvature models still assign uniform geometric resolution to structural directions with different densities and separation needs. Second, relational evidence is not always reliable: sophisticated bots forge heterophilic connections with genuine users, causing neighborhood aggregation to mix bot and human signals and dilute account-level evidence. We propose \textsc{SAHG} (Sector-Anisotropic Hyperbolic Graph), addressing both challenges. \textsc{SAHG} learns a direction-dependent curvature field $\gamma(u)$ that adapts geometric resolution across structural directions, and uses sector prototypes to convert angular concentration and alignment into classifier-readable features. To prevent contaminated aggregation from overwhelming account-level evidence, \textsc{SAHG} encodes per-account features and graph-neighborhood representations in two independent SAH channels, fusing them only at the classifier. Experiments on Fox8-23, BotSim-24, and MGTAB show that \textsc{SAHG} achieves the highest accuracy and F1 on all three benchmarks, outperforming feature-based, graph-based, LLM-based, and isotropic hyperbolic baselines. Ablation and geometric analyses confirm the effectiveness of the anisotropic geometry and dual-channel design.
Tsinghua AI