The widespread adoption of IoT devices has transformed automation and connectivity across multiple sectors. These devices depend heavily on wireless communication, providing flexibility and enabling real-time data exchange. The unique traffic patterns they generate, shaped by protocol usage, communication frequency, and data exchange behaviors facilitate precise device identification. These patterns can be leveraged to classify devices based solely on their network activity. Current approaches to IoT device identification rely on single machine-learning classifiers trained on historical traffic data. However, these systems face critical limitations, including an inability to detect new devices, failure to adapt to shifting traffic patterns, and challenges with imbalanced data representation, thus requiring frequent re-training of the classifier. To address these challenges, we propose UMIoT, a dynamic and adaptive Multi-Classifier based framework for device identification. Unlike traditional approaches, UMIoT employs a unique classifier for each device, enhancing identification accuracy and adaptability. Our study evaluates UMIoT's performance and compares with existing device identification approaches using metrics such as accuracy, precision, recall, and F1-score. Our experiments demonstrate that UMIoT achieves 100% accuracy for most devices, with an overall average device identification accuracy of 95.58% across the network. Despite employing multiple classifiers to determine the origin of traffic, UMIoT maintains a low prediction time of 0.2 seconds for 1000 packets, comparable to state-of-theart single-classifier approaches. Additionally, with UMIoT's 60% classifier accuracy threshold, devices entering the network are accurately detected as new devices without misclassifying their traffic as originating from existing devices.

The rapid growth in the number of wireless IoT devices has introduced new privacy challenges. Adversaries can exploit captured wireless traffic to profile and identify specific devices within the network. While several device identification frameworks have been developed to classify and identify devices, researchers have proposed methods such as traffic padding, shaping, and cover traffic injection to counteract identification attempts. However, these approaches often prove ineffective when adversaries gain access to the network. In this study, we propose a GAN-based traffic generation and injection framework designed to enhance device privacy against traffic analysis attacks, even in the presence of local adversaries. Our approach generates highly realistic network traffic and achieves a 98.5% success rate in seamlessly injecting packets into the network without any observable issues. By reducing the prediction confidence of multiple device identification approaches in predicting the origin of network traffic, our framework effectively enhances the privacy of IoT devices. Furthermore, the proposed solution incurs minimal performance overhead, making it a practical and efficient approach to addressing the growing privacy challenges in wireless networks.

The proliferation of IoT devices has revolutionized automation and connectivity across various industries. These devices rely extensively on wireless communication, enabling flexibility and real-time data exchange. The unique traffic patterns they produce, shaped by protocol usage, communication frequency, and data exchange behaviors allow for accurate device identification based solely on network activity. Previous research on IoT device identification has shown promise but faces key limitations including scalability, requiring frequent retraining for new devices, and are computationally intensive and unsuitable for real-time use. Reliance on spoofable attributes like IP and MAC addresses, or documentation-based profiling, further reduces reliability. To overcome these limitations, this study introduces UMIoT, an adaptive and dynamic Multi-Classifier framework for IoT device identification. UMIoT is trained on packet-streams, assigns a dedicated classifier to each device, improving accuracy, scalability, and adaptability. Furthermore, UMIoT can efficiently detect the presence of new devices without misclassifying their traffic as belonging to existing devices based on a parameterized confidencethreshold metric. Our experimental results demonstrate that UMIoT achieves high identification accuracy, maintains a low prediction time, enables rapid training for new emerging devices in the network, and operates with minimal storage overhead. Additionally, the results highlight the superiority of the proposed framework against existing device identification approaches both in terms of device identification accuracy and performance metrics including prediction time, storage overhead, and new device training time. The framework is also shown to be resilient against adversarial threats including traffic padding, shaping, and MAC address alteration.

There is a growing academic interest as well as commercial exploitation of millimetre-wave scanning radar for autonomous vehicle localisation and scene understanding. Although several datasets to support this research area have been released, they are primarily focused on urban or semi-urban environments. Nevertheless, rugged offroad deployments are important application areas which also present unique challenges and opportunities for this sensor technology. Therefore, the Oxford Offroad Radar Dataset (OORD) presents data collected in the rugged Scottish highlands in extreme weather. The radar data we offer to the community are accompanied by GPS/INS reference – to further stimulate research in radar place recognition. In total we release over 90 GiB of radar scans as well as GPS and IMU readings by driving a diverse set of four routes over 11 forays, totalling approximately 154 km of rugged driving. This is an area increasingly explored in literature, and we therefore present and release examples of recent open-sourced radar place recognition systems and their performance on our dataset. This includes a learned neural network, the weights of which we also release. The data and tools are made freely available to the community at oxford-robotics-institute.github.io/oord-dataset

This work proposes a fast deployment pipeline for visually-servoed robots which does not assume anything about either the robot - e.g. sizes, colour or the presence of markers - or the deployment environment. Specifically, we apply a learning based approach to reliably estimate the pose of a robot in the image frame of a 2D camera upon which a visual servoing control system can be deployed. To alleviate the time-consuming process of labelling image data, we propose a weakly supervised pipeline that can produce a vast amount of data in a small amount of time. We evaluate our approach on a dataset of remote camera images captured in various indoor environments demonstrating high tracking performances when integrated into a fully-autonomous pipeline with a simple controller. With this, we then analyse the data requirement of our approach, showing how it is possible to deploy a new robot in a new environment in fewer than 30.00 min.

This work presents a detailed study, characterization, and measurement of video latency in a real‐time video streaming application. The target application consists of an automatic control system in the form of a control station and the mini Remotely Operated Vehicle (ROV) equipped with a camera, which is controllable over local area network (LAN) and the Internet. Control signal transmission and feedback measurements to the operator usually impose real‐time constraints on the network channel. Similarly, the video stream, which is required for the normal system control and maneuvering, imposes further strict requirements on the network in terms of bandwidth and latency. Based on these requirements, controlling the system in real time through a standard Internet connection is a challenging task. The measurement of important network parameters like availability, bandwidth, and latency has become mandatory for remotely controlling the system in real time. It is necessary to establish a methodology for the measurement of video and network latency to improve the real‐time controllability and safety of the system as such measurement is not possible using existing solutions due to the following reasons: insufficient accuracy, relying on the Internet resources such as generic Network Time Protocol (NTP) servers, inability to obtain one‐way delay measurement, and many solutions only having support for web cameras. Here, an efficient, reliable, and cost‐effective methodology for the measurement of latency of a video stream over a LAN and the Internet is proposed. A dedicated stratum‐1 NTP server is used and the necessary software needed for acquiring and measuring the latency of a video stream from a generic IP camera as well as integration into the existing ROV control software was developed. Here, by using the software and dedicated clock synchronization equipment (NTP server), it was found that normal video latencies in a LAN were in the range of 488ms – 850ms, while latencies over the Internet were measured to be in the range of 558ms – 1211ms. It is important to note that the values were obtained by using a generic (off‐the‐shelf) IP camera and they represent the actual latencies which might be experienced during control over long range and across international territory borders.