Organizations: School of Cyber science at University of Science and Technology of China, Hefei 230026, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China · Institute of Data Science at the National University of Singapore, 119077, Singapore · State Key Laboratory of Software Development Environment, Beihang University, Beijing 1000191, China · in Systems Science from Beijing University of Posts and Telecommunications, Beijing 100876, China · National Engineering Laboratory for Big Data Analysis and Applications, Peking University, Beijing, 100871, P.R. China · Department of Computer Science, University of Illinois Chicago, Chicago, IL 60607, USA
Social bot detection is critical to the stability and security of online social platforms. However, current state-of-the-art bot detection models are largely developed in isolation, overlooking the benefits of leveraging shared detection patterns across platforms to improve performance and promptly identify emerging bot variants. The heterogeneity of data distributions and model architectures further complicates the design of an effective cross-platform and cross-model detection framework. To address these challenges, we propose FedRio (Personalized Federated Social Bot Detection with Cooperative Reinforced Contrastive Adversarial Distillation framework. We first introduce an adaptive message-passing module as the graph neural network backbone for each client. To facilitate efficient knowledge sharing of global data distributions, we design a federated knowledge extraction mechanism based on generative adversarial networks. Additionally, we employ a multi-stage adversarial contrastive learning strategy to enforce feature space consistency among clients and reduce divergence between local and global models. Finally, we adopt adaptive server-side parameter aggregation and reinforcement learning-based client-side parameter control to better accommodate data heterogeneity in heterogeneous federated settings. Extensive experiments on two real-world social bot detection benchmarks demonstrate that FedRio consistently outperforms state-of-the-art federated learning baselines in detection accuracy, communication efficiency, and feature space consistency, while remaining competitive with published centralized results under substantially stronger privacy constraints.
Figures & tables
Fig. 1: The proposed FedRio framework.
st=[rt1,pt1,ℓt1,…,rtK,ptK,ℓtK]
Algorithm 2 Client Parameter Update Based on Reinforcement Learning
Dataset
Total Nodes
Edges
Bots
Humans
Vendor-19
5,349
11,284
2,553
2,796
TwiBot-20
11,826
85,927
6,589
5,237
TABLE I: Statistics of the Datasets
Fig. 2: Visualization of data heterogeneity. The darker color means more training samples with a label available to the client.
Metric
Accuracy
F1
Setting
α=1
α=0.5
α=0.1
α=0.05
α=1
α=0.5
α=0.1
α=0.05
FedAvg
71.30 ± 0.60
61.06 ± 1.52
60.88 ± 2.85
59.81 ± 2.48
68.48 ± 4.08
66.78 ± 0.15
65.70 ± 0.65
66.61 ± 0.01
FedProx
84.37 ± 0.43
78.25 ± 1.02
51.86 ± 0.04
63.27 ± 2.32
84.99 ± 0.60
76.70 ± 0.67
77.16 ± 0.61
67.07 ± 0.15
FedDF
86.37 ± 1.23
80.17 ± 2.21
63.16 ± 1.37
67.01 ± 1.78
-
-
-
-
FedEnsemble
81.12 ± 2.22
76.70 ± 1.21
64.51 ± 2.56
68.05 ± 1.15
80.87 ± 8.04
67.77 ± 1.20
69.45 ± 3.38
67.35 ± 0.40
FedDistill
79.68 ± 0.58
68.77 ± 1.13
52.88 ± 0.06
70.25 ± 0.39
77.20 ± 0.09
69.16 ± 1.00
67.08 ± 0.37
67.57 ± 0.17
TABLE II: Comparison of the average maximum accuracy of different methods for social bot detection on Dataset Vendor-19 (%).
Metric
Accuracy
F1
Setting
α=1
α=0.5
α=0.1
α=0.05
α=1
α=0.5
α=0.1
α=0.05
FedAvg
54.04 ± 0.50
55.41 ± 1.35
51.37 ± 0.77
52.46 ± 0.02
53.37 ± 0.01
55.06 ± 2.96
50.40 ± 0.00
50.41 ± 0.01
FedProx
74.34 ± 0.06
73.32 ± 0.25
51.86 ± 0.04
52.30 ± 0.63
78.46 ± 0.17
77.33 ± 0.45
50.08 ± 0.00
51.02 ± 0.25
FedDF
72.12 ± 1.96
71.25 ± 1.03
55.23 ± 1.32
53.35 ± 1.41
-
-
-
-
FedEnsemble
55.98 ± 2.55
54.15 ± 0.04
54.21 ± 0.04
54.15 ± 0.04
68.63 ± 16.88
45.73 ± 5.23
47.38 ± 5.53
38.99 ± 1.74
FedDistill
64.11 ± 0.29
63.34 ± 0.56
50.00 ± 0.00
54.30 ± 0.05
66.04 ± 1.59
63.99 ± 0.27
50.08 ± 0.00
52.50 ± 0.37
TABLE III: Comparison of the average maximum accuracy of different methods for social bot detection on Dataset TwiBot-20 (%).
Fig. 3: Loss dynamics during training under different data consistency parameters and loss functions.
Fig. 4: Hyperparameter Sensitivity ( γ,τ,μ ) of FedACK on Vendor-19 under diferent data heterogeneity settings ( α ).
Fig. 5: Learning Curve of (a-b) Vendor-19 and (c-d) TwiBot-20 in 100 communication rounds in different α settings.
Dataset
Vendor-19
TwiBot-20
Setting
α=1(85)
α=0.5(75)
α=1(75)
α=0.5(70)
FedAvg
unreached
unreached
unreached
unreached
FedProx
unreached
50.2 ± 1.3
13.3 ± 2.8
44.4 ± 8.4
FedDF
unreached
unreached
unreached
unreached
FedDistill
unreached
60.3 ± 12.6
unreached
unreached
FedGen
25.2 ± 3,7
7.5 ± 1.2
10.6 ± 0.9
16.6 ± 2.2
TABLE IV: The round number to reach the target accuracy on Vendor-19 (80%,70%) and TwiBot-20 (70%,65%) .
Fig. 6: Decision boundaries and feature space of two randomly selected clients from FedRio trained on Vendor-19. The x-axis and y-axis represent the values of the 2-dimensional features output by ε described in Sec V-D .
Dataset
Vendor-19
Setting
α=1
α=0.5
α=0.1
α=0.05
FedRio -NA&NR&NC
88.58 ± 1.91
87.05 ± 2.03
76.04 ± 3.40
75.27 ± 2.50
FedRio -NA&NR
93.28 ± 0.94
87.28 ± 01.32
77.92 ± 1.78
70.41 ± 1.73
FedRio -NA
94.19 ± 1.23
89.37 ± 0.92
78.02 ± 2.16
77.57 ± 1.93
FedRio -NC
89.38 ± 1.45
88.31 ± 1.63
76.31 ± 1.27
71.12 ± 1.72
FedRio -NR
92.37 ± 1.03
90.07 ± 0.79
73.89 ± 2.19
70.27 ± 2.53
TABLE V: Comparison of the average maximum accuracy (%) of different methods with/without AGA (NA), with/without RL (NR), and with/without the adaptive message-passing module (NC). Gain is the disparity between FedRio and other baselines.
TABLE VI: Contextual comparison between centralized social bot detectors (published results on TwiBot-20 with full data access) and FedRio (federated setting with local subgraph access only). Centralized results are cited from the original papers. “ † ” indicates results cited from LMBot. [ 36 ] .
Yingguang Yang received the Ph.D. degree in the School of Cyber Science at University of Science and Technology of China. His research interests include machine learning, data mining, and social bot detection.
Table 14
Hao Liu is currently a master’s student in the School of Cyber Science and Technology at the University of Science and Technology of China. His research interests include fairness, federated learning and graph neural networks.
Table 15
Xin Zhang is currently a master’s student in the School of Cyber Science and Technology at the University of Science and Technology of China. Her research interests include fairness, federated learning and privacy policy security under the guidance of LLM.
Table 16
Yunhui Liu is working toward the Ph.D. degree with the Software Institute, Nanjing University, China. His research interests include graph machine learning and self-supervised learning.
Table 17
Yutong Xia is currently a PhD student at the Institute of Data Science, National University of Singapore. She has published several papers in refereed conferences, such as NeurIPS, IJCAI, AAAI, and SIGSPATIAL. Her research interests mainly lie in spatio-temporal data mining and graph neural networks.
Table 18
Qi Wu is currently a master’s student in the School of Cyber Science and Technology at University of Science and Technology of China. His research interests include multi-view learning, social bot detection and graph neural networks.
Table 19
Hao Peng is currently a Professor at the School of Cyber Science and Technology in Beihang University. His current research interests include machine learning, deep learning, and reinforcement learning. He is the Associate Editor of the International Journal of Machine Learning and Cybernetics (IJMLC).
Table 20
Taoran Liang received the M.Sc. degree in Systems Science from Beijing University of Posts and Telecommunications, China. His research interests include reinforcement learning for large language models (LLMs) and graph neural networks (GNNs).
Table 21
Bin Chong received the Ph.D. degree in physical chemistry from the Peking University. He is currently an associate professor in the Peking University. His research interest includes machine learning, molecular modelling and digital transformation.
Table 22
Tieke He received the B.E. and Ph.D. degrees in software engineering from the Software Institute, Nanjing University, Jiangsu, China. He is currently an Associate Professor with the Software Institute, Nanjing University. His research interests lie in intelligent software engineering, knowledge graph, and question answering.
Table 23
Philip S. Yu is a Distinguished Professor and the Wexler Chair in Information Technology at the Department of Computer Science, University of Illinois Chicago. He is a Fellow of the ACM and IEEE. Dr. Yu has published more than 1,200 referred conference and journal papers cited more than 190,000 times with an H-index of 195. He has applied for more than 300 patents. Dr. Yu was the Editor-in-Chief of ACM TKDD (2011-2017) and IEEE TKDE (2001-2004).
Social bot detection is pivotal for safeguarding the integrity of online information ecosystems. Although recent graph neural network (GNN) solutions achieve strong results, they remain hindered by two practical challenges: (i) severe class imbalance arising from the high cost of generating bots, and (ii) topological noise introduced by bots that skillfully mimic human behavior and forge deceptive links. We propose the Reinforcement-guided graph Augmentation social Bot detector (RABot), a multi-granularity graph-augmentation framework that addresses both issues in a unified manner. RABot employs a neighborhood-aware oversampling strategy that linearly interpolates minority-class embeddings within local subgraphs, thereby stabilizing the decision boundary under low-resource regimes. Concurrently, a reinforcement-learning-driven edge-filtering module combines similarity-based edge features with adaptive threshold optimization to excise spurious interactions during message passing, yielding a cleaner topology. Extensive experiments on three real-world benchmarks and four GNN backbones demonstrate that RABot consistently surpasses state-of-the-art baselines. In addition, since its augmentation and filtering modules are orthogonal to the underlying architecture, RABot can be seamlessly integrated into existing GNN pipelines to boost performance with minimal overhead.
Longlong Zhang, Xi Wang, Haotong Du +3
School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University · Shenzhen Research Institute, Northwestern Polytechnical University · School of Automation Science and Engineering, Xi’an Jiaotong University +1
We study the application of federated learning (FL) to indoor fire detection. Such fire-detection systems use edge cameras that record sensitive footage which cannot easily be collected at a central server. Existing federated solutions leave three practical obstacles unaddressed: limited uplink bandwidth, Byzantine (malicious or faulty) clients, and unconditional trust in a single, permanently fixed aggregation server. Our main contributions address all three. In particular, we provide (i) a curated indoor fire-detection dataset assembled from eight public sources; (ii) an edge-deployable detector whose model updates are compressed up to 10 times with only a small loss in balanced accuracy; and (iii) a semi-decentralized Byzantine-robust FL method that combines history-aware aggregation with a rotating coordinator, evicting stealthy attacks that per-round filters miss while removing the fixed-server single point of failure. On the held-out test set the rotating-coordinator method matches its fixed-server counterpart in accuracy and detection speed, and a physically distributed six-node cloud deployment confirms feasibility.
Georgia Argyrou, Aymen Bahroun, Hedi Fendri +1
Department of Computer Science, Aalto University, Espoo, Finland · Kudelski Labs
We present a comprehensive overview of the challenges and opportunities in social bot detection in the context of the rise of sophisticated AI-based chatbots. By examining the state of the art in social bot detection techniques and the more salient real-world application to date, we identify gaps and emerging trends in the field, with a focus on addressing the unique challenges posed by AI-generated conversations and behaviors. We suggest potentially promising opportunities and research directions in social bot detection, including (i) the use of generative agents for synthetic data generation, testing and evaluation; (ii) the need for multimodal and cross-platform detection based on network and behavioral signatures of coordination and influence; (iii) the opportunity to extend bot detection to non-English and low-resource language settings; and, (iv) the room for development of collaborative, federated learning detection models that can help facilitate cooperation between different organizations and platforms while preserving user privacy.