TRIDENT: Temporal Reasoning and Detection of Emerging Network Threats
Lists
Only you see this
Abstract
The rapid spread of misinformation on social media threatens public discourse, trust, and decision-making. Existing rumor detection methods—ranging from multimodal fusion to graph-based reasoning—have achieved promising results but often struggle to capture the multiview, heterogeneous, evolving, and adversarial nature of real-world rumor propagation. Common limitations include oversimplified graph structures, shallow temporal modeling (TM), and limited semantic grounding or robustness. To address these challenges, we propose temporal reasoning and detection of emerging network threats (TRIDENT), a unified and interpretable framework that represents rumor events as multiview heterogeneous temporal graphs enriched with external knowledge. TRIDENT integrates a novel partial differential equation–graph convolutional network (PDE-GCN) module for continuous-time temporal encoding, cross-view attention for joint reasoning over user interactions, content semantics, and propagation structure, and multimodal adversarial training to defend against label-preserving manipulations in both text and graph domains. Comprehensive evaluations on four benchmark datasets, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Twitter15</i>, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Twitter16</i>, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Weibo</i>, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PHEME</i>, show that TRIDENT consistently outperforms state-of-the-art baselines, with especially strong gains on challenging rumor types such as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">false</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">unverified</i> claims. These results highlight the importance of unifying TM, semantic grounding, and adaptive multiview graph reasoning for robust and explainable rumor detection in dynamic social ecosystems.
BibTeX
@article{almousa2025trident,
author = {Ghadah Almousa and Yugyung Lee},
title = {{TRIDENT: Temporal Reasoning and Detection of Emerging Network Threats}},
journal = {IEEE Transactions on Computational Social Systems},
year = {2025},
doi = {10.1109/tcss.2025.3621180},
}Loading related content...