Federated Lightweight Transformer for Network-Layer Cyberattack Detection in O-RAN
Authors: Hong Nhung Nguyen, Abdulahi Badrudeen, Yekaterina Kim, Truong Thu Huong, Sunwoo Kim
Organizations: Department of Electronic Engineering, Hanyang University, Seoul, South Korea · School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam
Open Radio Access Network (O-RAN) improves radio access network flexibility through disaggregation, open interfaces, and programmable RAN Intelligent Controllers (RICs). However, the same openness and distribution increase the attack surface and make centralized intrusion detection difficult to scale across heterogeneous RAN sites. This paper presents a federated lightweight Transformer framework for privacy-preserving network-layer cyberattack detection in O-RAN. Each participating site trains a compact Transformer locally on temporally ordered network-flow records, while only model parameters are shared with a federated coordinator. To model realistic site heterogeneity, the client datasets are partitioned according to a Dirichlet distribution, resulting in non-independent and identically distributed (non-IID) local data. The local detector uses feature projection, positional encoding, multi-head self-attention, feed-forward layers, and temporal pooling to classify five network-layer attack categories: ICMP, Slowloris, SYN, TCP-ACK, and UDP. Experiments on the NetsLab 5G O-RAN intrusion-detection dataset show an overall accuracy of 94.89 % and a macro-F1 score of 81.09 %.
Figures & tables
Fig. 1: Overview of the federated lightweight Transformer architecture for distributed O-RAN network-layer cyberattack detection.
Parameter
Value
Number of clients
5
Dirichlet α
0.5
Embedding dimension
64
Transformer encoder layers
2
Attention heads
4
Feed-forward dimension
128
TABLE I: Experimental configuration
Class
Precision (%)
Recall (%)
F1 (%)
ICMP
86.96
32.79
47.62
Slowloris
65.94
77.84
71.40
SYN
99.71
97.99
98.84
TCP-ACK
98.24
98.04
98.14
UDP
85.39
93.95
89.47
Macro average
87.25
80.12
81.09
TABLE II: Class-Wise Detection Performance
Fig. 2: Confusion matrix of the proposed method’s output on the test dataset.
Network intrusion detection identifies malicious or abnormal network activity to help protect computers, connected devices, and critical infrastructure.
Bangladesh University of Business and Technology (BUBT), Mirpur-2, Dhaka-1216, Bangladesh · Jagannath University, Dhaka, Bangladesh · University of New South Wales (UNSW), ACT 2601, Australia