Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection

2026-01-30

AI Summary

This work addresses the limited robustness of existing graph neural network (GNN)-based social bot detection methods against realistic adversarial attacks. To bridge the gap between theoretical attacks and practical deployment, we propose BOCLOAK, a novel framework that, for the first time, integrates optimal transport theory into adversarial attacks on social bots. BOCLOAK generates sparse, plausible, and interpretable perturbations through edge editing and node injection, operating under spatiotemporal and domain-specific constraints. By leveraging the geometric structure of optimal transport to characterize behavioral discrepancies between humans and bots, our approach establishes a lightweight attack paradigm. Experimental results across three real-world datasets demonstrate that BOCLOAK improves attack success rates by up to 80.13% while reducing GPU memory consumption by 99.80%, substantially outperforming current state-of-the-art baselines.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Adversarial Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely on Graph Neural Networks (GNNs). However, the effectiveness of these GNN-based detectors in real-world settings remains poorly understood. In practice, attackers continuously adapt their strategies as well as must operate under domain-specific and temporal constraints, which can fundamentally limit the applicability of existing attack methods. As a result, there is a critical need for robust GNN-based bot detection methods under realistic, constraint-aware attack scenarios. To address this gap, we introduce BOCLOAK to systematically evaluate the robustness of GNN-based social bot detection via both edge editing and node injection adversarial attacks under realistic constraints. BOCLOAK constructs a probability measure over spatio-temporal neighbor features and learns an optimal transport geometry that separates human and bot behaviors. It then decodes transport plans into sparse, plausible edge edits that evade detection while obeying real-world constraints. We evaluate BOCLOAK across three social bot datasets, five state-of-the-art bot detectors, three adversarial defenses, and compare it against four leading graph adversarial attack baselines. BOCLOAK achieves up to 80.13% higher attack success rates while using 99.80% less GPU memory under realistic real-world constraints. Most importantly, BOCLOAK shows that optimal transport provides a lightweight, principled framework for bridging the gap between adversarial attacks and real-world bot detection.

Problem

• Graph Neural Networks
• Adversarial Attacks
• Bot Detection
• Optimal Transport
• Realistic Constraints

Innovation

• Optimal Transport
• Graph Neural Networks
• Adversarial Attacks
• Bot Detection
• Constraint-aware Attack