RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction

作者：Yingguang Yang, Xianghua Zeng, Q. M. Jonathan Wu, Hao Peng, Yutong Xia, Hao Liu, Bin Chong, Philip S. Yu · 发表于：ACM Transactions on Knowledge Discovery from Data · 年份：2026 · DOI：10.1145/3847302 · 研究领域：Advanced Graph Neural Networks、Misinformation and Its Impacts、Spam and Phishing Detection

Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from researchers, leading to the development of numerous detection technologies. However, the vulnerability and robustness of these detection methods is still underexplored. Existing Graph Neural Network (GNN)-based methods cannot be directly applied due to the issues of limited control over social agents , the black-box nature of bot detectors , and the heterogeneity of bots . To address these challenges, this paper proposes the first adversarial multi-agent R einf o rcement learning framework for social B ot c on tr o l attacks ( RoBC trl ) targeting GNN-based social bot detectors. Specifically, we use a diffusion model to generate high-fidelity bot accounts by reconstructing existing account data with minor modifications, thereby evading detection on social platforms. To the best of our knowledge, this is the first application of diffusion models to mimic the behavior of evolving social bots effectively. We then employ a Multi-Agent Reinforcement Learning (MARL) method to simulate bots’ adversarial behavior. We categorize social accounts based on their influence and budget. Different agents are then employed to control bot accounts across various categories, optimizing the attachment strategy through reinforcement learning. Additionally, a hierarchical state abstraction based on structural entropy is ...