The advancement of 5G and NextG networks through Open Radio Access Network (O-RAN) architecture marks a transformative shift towards more virtualized, modular, and disaggregated configurations. A critical component within this O-RAN architecture is the RAN Intelligent Controller (RIC), which facilitates the management and control of the RAN through sophisticated machine learning-driven software microservices known as xApps. These xApps rely on accessing a diverse range of sensitive data from RAN and User Equipment (UE), stored in the near Real-Time RIC (Near-RT RIC) database. The inherent nature of this shared, multi-vendor, and open environment significantly raises the risk of unauthorized sensitive RAN/UE data exposure. In response to these privacy concerns, this paper proposes a privacy-preserving zero-trust RIC (dubbed as, ZT-RIC) framework that preserves RAN/UE data privacy within the RIC platform (i.e., shared RIC database, xA$p$p, and E2 interface). The underlying idea is to employ a computationally efficient cryptographic technique called Inner Product Functional Encryption (IPFE) to encrypt the RAN/UE data at the base station, thus, preventing data leaks over the E2 interface and shared RIC database. Furthermore, ZT-RIC customizes the xAp$p$'s inference model by leveraging the inner product operations on encrypted data supported by IPFE to enable xAp$p$to make accurate inferences without data exposure. For evaluation purposes, we leverage a state-of-the-art InterClass xApp, which utilizes RAN key performance metrics (KPMs) to identify jamming signals within the wireless network. Prototyping on an LTE/5G O-RAN testbed demonstrates that ZT-RIC not only ensures data privacy/confidentiality but also guarantees a desired model accuracy of 97.9% in detecting jamming signals as well as meeting stringent sub-second timing requirement with a round-trip time (RTT) of 0.527 seconds.

Recent advancements in artificial intelligence (AI) and edge computing have accelerated the development of machine-centric applications (MCAs), such as smart surveillance systems. In these applications, video cameras and sensors offload inference tasks like license plate recognition and vehicle tracking to remote servers due to local computing and energy constraints. However, legacy network solutions, designed primarily for human-centric applications, struggle to reliably support these MCAs, which demand heterogeneous and fluctuating quality of service (QoS) (due to diverse application inference tasks), further challenged by dynamic wireless network conditions and limited spectrum resources. To tackle these challenges, we propose an Application Context-aware Cross-layer Optimization and Resource Design (ACCORD) framework. This innovative framework anticipates the evolving demands of MCAs in real time, quickly adapting to provide customized QoS and optimal performance, even for the most dynamic and unpredictable MCAs. This also leads to improved network resource management and spectrum utilization. ACCORD operates as a closed feedback-loop system between the application client and network and consists of two key components: (1) Building Application Context: It focuses on understanding the specific context of MCA requirements. Contextual factors include device capabilities, user behavior (e.g., mobility speed), and network channel conditions, and (2) Cross-layer Network Parameter Configuration: Utilizing a deep reinforcement learning (DRL) approach, this component leverages the contextual information to optimize network configuration parameters across various layers, including physical (PHY), medium access control (MAC), and radio link control (RLC), as well as the application layer, to meet the desired QoS requirement in realtime. Extensive evaluation with the 3GPP-compliant MATLAB 5G toolbox demonstrates the practicality and effectiveness of our proposed ACCORD framework.

This work presents SPARC (Spatio-Temporal Adaptive Resource Control), a novel approach for multi-site spectrum management in NextG cellular networks. SPARC addresses the challenge of limited licensed spectrum in dynamic environments. We leverage the O-RAN architecture to develop a multi-timescale RAN Intelligent Controller (RIC) framework, featuring an xApp for near-real-time interference detection and localization, and a μApp for real-time intelligent resource allocation. By utilizing base stations as spectrum sensors, SPARC enables efficient and fine-grained dynamic resource allocation across multiple sites, enhancing signal-to-noise ratio (SNR) by up to 7dB, spectral efficiency by up to 15%, and overall system throughput by up to 20%.

While the open architecture, open interfaces, and integration of intelligence within Open Radio Access Network technology hold the promise of transforming 5G and 6G networks, they also introduce cybersecurity vulnerabilities that hinder its widespread adoption. In this paper, we conduct a thorough system-level investigation of cyber threats, with a specific focus on machine learning (ML) intelligence components known as xApps within the O-RAN's near-real-time RAN Intelligent Controller (near-RT RIC) platform. Our study begins by developing a malicious xApp designed to execute adversarial attacks on two types of test data - spectrograms and key performance metrics (KPMs), stored in the RIC database within the near-RT RIC. To mitigate these threats, we utilize a distillation technique that involves training a teacher model at a high softmax temperature and transferring its knowledge to a student model trained at a lower softmax temperature, which is deployed as the robust ML model within xApp. We prototype an over-the-air LTE/5G O-RAN testbed to assess the impact of these attacks and the effectiveness of the distillation defense technique by leveraging an ML-based Interference Classification (InterClass) xApp as an example. We examine two versions of InterClass xApp under distinct scenarios, one based on Convolutional Neural Networks (CNNs) and another based on Deep Neural Networks (DNNs) using spectrograms and KPMs as input data respectively. Our findings reveal up to 100% and 96.3% degradation in the accuracy of both the CNN and DNN models respectively resulting in a significant decline in network performance under considered adversarial attacks. Under the strict latency constraints of the near-RT RIC closed control loop, our analysis shows that the distillation technique outperforms classical adversarial training by achieving an accuracy of up to 98.3% for mitigating such attacks.