arXiv subjects

Julia Boone

Publications and source records attributed to Julia Boone.

5 recordsLinked to original sources

arXiv2026

AtlasRAN: Timing-Aware Evaluation of Open-source 5G Platforms for Integrated Wireless Testbeds

Open-source fifth-generation (5G) and Open Radio Access Network (O-RAN) experiments span simulation, host operating system (host-OS) emulation, software-defined radio hardware-in-the-loop testing, Open Radio Unit fronthaul deployments, wireless digital twins, and accelerator-backed radio access network (RAN) runtimes. These environments may expose similar interfaces while preserving different timing, input/output, synchronization, buffering, transport, and observability; functional compatibility is therefore not timing fidelity. This paper presents AtlasRAN, a claim-to-capability framework for deciding what an open-source 5G platform can credibly measure. It combines two reference paths, an execution-regime matrix, and a measurement-backed case study comparing OpenAirInterface (OAI) radio-frequency simulator (RFSim) with the Sionna Research Kit (Sionna-RK), which offloads low-density parity-check (LDPC) decoding to CUDA while retaining the surrounding OAI host-OS path. From one to six users, aggregate uplink goodput falls from 114.59 to 35.09 Mb/s for OAI and from 103.34 to 35.01 Mb/s for Sionna-RK. At six users, both RFSim real-time factors are approximately 0.55, despite estimated cumulative LDPC work of 1.09~ms per transport block for OAI and 0.37 ms for Sionna-RK. Timing-normalized service remains 60.7-63.6~Mb per emulated second across complete runs, while falling host and accelerator utilization is consistent with an under-fed decoder. A twelve-user run is retained only as failure-region evidence because end-of-test traffic summaries are absent. The practical takeaway is that integrated wireless testbeds, edge platforms, artificial-intelligence-enabled RANs, and digital twins should report timing discipline, transport path, memory movement, and observability as first-class experimental variables.

cs.NI↗

arXiv2026

Six Times to Spare: Characterizing GPU-Accelerated 5G LDPC Decoding for Edge-RSU Communications

Ultra-reliable low-latency vehicular communications (URLLC) require sufficient physical-layer (PHY) compute headroom at the network edge, where roadside units (RSUs) and compact next-generation base stations (gNBs) must meet strict timing constraints while co-hosting higher-layer services. In 5G New Radio (5G NR), low-density parity-check code (LDPC) decoding is a latency-sensitive iterative PHY workload whose cost scales with both workload parallelism and decoder iteration budget, making it a potential bottleneck on general-purpose central processing units (CPUs). This paper presents a reproducible, telemetry-backed microbenchmark derived from the Sionna LDPC5G baseline to characterize the compute headroom obtained through graphics processing unit (GPU) offload on compact heterogeneous edge platforms. We evaluate decoder behavior across multiple processor architectures and a wide range of batch sizes and iteration counts, with emphasis on dense operating regimes relevant to edge provisioning. Results show that GPU acceleration substantially increases LDPC throughput, reduces amortized decode service time, and shifts compute pressure away from the CPU, thereby improving the feasibility of meeting edge-RSU timing budgets under heavy parallel workloads. These findings indicate that GPU offload can provide substantial spare PHY compute margin for compact vehicular edge platforms, making dense decode workloads more practical within realistic edge power and timing constraints.

cs.DC↗

arXiv2026

Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems

The paradigm of Earth Observation analysis is shifting from static deep learning models to autonomous agentic AI. Although recent vision foundation models and multimodal large language models advance representation learning, they often lack the sequential planning and active tool orchestration required for complex geospatial workflows. This survey presents the first comprehensive review of agentic AI in remote sensing. We introduce a unified taxonomy distinguishing between single-agent copilots and multi-agent systems while analyzing architectural foundations such as planning mechanisms, retrieval-augmented generation, and memory structures. Furthermore, we review emerging benchmarks that move the evaluation from pixel-level accuracy to trajectory-aware reasoning correctness. By critically examining limitations in grounding, safety, and orchestration, this work outlines a strategic roadmap for the development of robust, autonomous geospatial intelligence.

cs.CV↗

arXiv2025

Securing Swarms: Cross-Domain Adaptation for ROS2-based CPS Anomaly Detection

Cyber-physical systems (CPS) are being increasingly utilized for critical applications. CPS combines sensing and computing elements, often having multi-layer designs with networking, computational, and physical interfaces, which provide them with enhanced capabilities for a variety of application scenarios. However, the combination of physical and computational elements also makes CPS more vulnerable to attacks compared to network-only systems, and the resulting impacts of CPS attacks can be substantial. Intelligent intrusion detection systems (IDS) are an effective mechanism by which CPS can be secured, but the majority of current solutions often train and validate on network traffic-only datasets, ignoring the distinct attacks that may occur on other system layers. In order to address this, we develop an adaptable CPS anomaly detection model that can detect attacks within CPS without the need for previously labeled data. To achieve this, we utilize domain adaptation techniques that allow us to transfer known attack knowledge from a network traffic-only environment to a CPS environment. We validate our approach using a state-of-the-art CPS intrusion dataset that combines network, operating system (OS), and Robot Operating System (ROS) data. Through this dataset, we are able to demonstrate the effectiveness of our model across network traffic-only and CPS environments with distinct attack types and its ability to outperform other anomaly detection methods.

cs.CR↗

arXiv2025

A Joint Reconstruction-Triplet Loss Autoencoder Approach Towards Unseen Attack Detection in IoV Networks

Internet of Vehicles (IoV) systems, while offering significant advancements in transportation efficiency and safety, introduce substantial security vulnerabilities due to their highly interconnected nature. These dynamic systems produce massive amounts of data between vehicles, infrastructure, and cloud services and present a highly distributed framework with a wide attack surface. In considering network-centered attacks on IoV systems, attacks such as Denial-of-Service (DoS) can prohibit the communication of essential physical traffic safety information between system elements, illustrating that the security concerns for these systems go beyond the traditional confidentiality, integrity, and availability concerns of enterprise systems. Given the complexity and volume of data generated by IoV systems, traditional security mechanisms are often inadequate for accurately detecting sophisticated and evolving cyberattacks. Here, we present an unsupervised autoencoder method trained entirely on benign network data for the purpose of unseen attack detection in IoV networks. We leverage a weighted combination of reconstruction and triplet margin loss to guide the autoencoder training and develop a diverse representation of the benign training set. We conduct extensive experiments on recent network intrusion datasets from two different application domains, industrial IoT and home IoT, that represent the modern IoV task. We show that our method performs robustly for all unseen attack types, with roughly 99% accuracy on benign data and between 97% and 100% performance on anomaly data. We extend these results to show that our model is adaptable through the use of transfer learning, achieving similarly high results while leveraging domain features from one domain to another.

cs.CR↗