SAJD: Self-Adaptive Jamming Attack Detection in AI/ML Integrated 5G O-RAN Networks

TL;DR

This work addresses jamming in AI/ML–enabled 5G O-RAN by proposing SAJD, a fully closed-loop jammer-detection framework that integrates non-RT RIC telemetry, labeler rApps for automatic data labeling, and near-RT xApps for real-time inference, with a ClearML-based pipeline for continuous training and model deployment. The architecture comprises a Labeler rApp (unsupervised labeling via Gaussian Mixture Models), a Training Manager rApp (automatic retraining and deployment), an Interference Detection xApp (real-time classification), and a ClearML training host (MLOps orchestration). Experimental results on O-RAN testbeds demonstrate that SAJD achieves higher accuracy and better adaptation to unseen interference than offline, manually labeled baselines, maintaining robust performance across dynamic scenarios with no service disruption. The framework thus enables autonomous, production-grade interference management in future RAN deployments, while acknowledging concerns about data-poisoning and adversarial threats that warrant further study.

Abstract

The open radio access network (O-RAN) enables modular, intelligent, and programmable 5G network architectures through the adoption of software-defined networking (SDN), network function virtualization (NFV), and implementation of standardized open interfaces. It also facilitates closed loop control and (non/near) real-time optimization of radio access network (RAN) through the integration of non-real-time applications (rApps) and near-real-time applications (xApps). However, one of the security concerns for O-RAN that can severely undermine network performance and subject it to a prominent threat to the security & reliability of O-RAN networks is jamming attacks. To address this, we introduce SAJD-a self-adaptive jammer detection framework that autonomously detects jamming attacks in artificial intelligence (AI) / machine learning (ML)-integrated O-RAN environments. The SAJD framework forms a closed-loop system that includes near-real-time inference of radio signal jamming interference via our developed ML-based xApp, as well as continuous monitoring and retraining pipelines through rApps. Specifically, a labeler rApp is developed that uses live telemetry (i.e., KPIs) to detect model drift, triggers unsupervised data labeling, executes model training/retraining using the integrated & open-source ClearML framework, and updates deployed models on the fly, without service disruption. Experiments on O-RAN-compliant testbed demonstrate that the SAJD framework outperforms state-of-the-art (offline-trained with manual labels) jamming detection approach in accuracy and adaptability under various dynamic and previously unseen interference scenarios.

Figures (5)

• Figure 1: SAJD closed-loop framework.
• Figure 2: Illustration of the rate of change between two successive data points.
• Figure 3: Labeler rApp prediction performance for different scenarios.
• Figure 4: Comparison of interference detection between the SAJD and the SOTA approach under two different scenarios.
• Figure 5: Comparison of interference detection accuracy across windows of sequential scenes (1a–2f).