Autonomous Vehicles (AVs) rely on real-time processing of natural images and videos for scene understanding and safety assurance through proactive object detection. Traditional methods have primarily focused on 2D object detection, limiting their spatial understanding. This study introduces a novel approach by leveraging 3D object detection in conjunction with augmented reality (AR) ecosystems for enhanced real-time scene analysis. Our approach pioneers the integration of a synthetic dataset, designed to simulate various environmental, lighting, and spatiotemporal conditions, to train and evaluate an AI model capable of deducing 3D bounding boxes. This dataset, with its diverse weather conditions and varying camera settings, allows us to explore detection performance in highly challenging scenarios. The proposed method also significantly improves processing times while maintaining accuracy, offering competitive results in conditions previously considered difficult for object recognition. The combination of 3D detection within the AR framework and the use of synthetic data to tackle environmental complexity marks a notable contribution to the field of AV scene analysis. • A multimodal architecture for real-time 3D object detection in AV systems. • Efficient 3D bounding box prediction extrapolated from 2D images. • Novel synthetic dataset simulates diverse environmental conditions for AVs. • Comparative evaluation against state-of-the-art techniques for object detection.

Current methods for low- and few-shot object detection have primarily focused on enhancing model performance for detecting objects. One common approach to achieve this is by combining model finetuning with data augmentation strategies. However, little attention has been given to the energy efficiency of these approaches in data-scarce regimes. This paper seeks to conduct a comprehensive empirical study that examines both model performance and energy efficiency of custom data augmentations and automated data augmentation selection strategies when combined with a lightweight object detector. The methods are evaluated in four different benchmark datasets in terms of their performance and energy consumption, providing valuable insights regarding reaching an optimal tradeoff between these two objectives. Additionally, to better quantify this tradeoff, we propose a novel metric named modified Efficiency Factor that combines both of these conflicting objectives in a single metric and thus enables gaining insights into the effectiveness of the examined models and data augmentation strategies when considering both performance and efficiency. Consequently, it is shown that while some broader guidelines regarding appropriate data augmentation selections can be provided based on the obtained performance and energy efficiency results, in many cases, the performance gains of data augmentation strategies are overshadowed by their increased energy usage, necessitating the development of more energy-efficient data augmentation strategies to address data scarcity.

The electrical grid has significantly evolved over the years, thus creating a smart paradigm, which is well known as the smart electrical grid. However, this evolution creates critical cybersecurity risks due to the vulnerable nature of the industrial systems and the involvement of new technologies. Therefore, in this paper, the ELECTRON architecture is presented as an integrated platform to detect, mitigate and prevent potential cyberthreats timely. ELECTRON combines both cybersecurity and energy defence mechanisms in a collaborative way. The key aspects of ELECTRON are (a) dynamic risk assessment, (b) asset certification, (c) federated intrusion detection and correlation, (d) Software Defined Networking (SDN) mitigation, (e) proactive islanding and (f) cybersecurity training and certification.

Modern Healthcare cyberphysical systems have begun to rely more and more on distributed AI leveraging the power of Federated Learning (FL). Its ability to train Machine Learning (ML) and Deep Learning (DL) models for the wide variety of medical fields, while at the same time fortifying the privacy of the sensitive information that are present in the medical sector, makes the FL technology a necessary tool in modern health and medical systems. Unfortunately, due to the polymorphy of distributed data and the shortcomings of distributed learning, the local training of Federated models sometimes proves inadequate and thus negatively imposes the federated learning optimization process and in extend in the subsequent performance of the rest Federated models. Badly trained models can cause dire implications in the healthcare field due to their critical nature. This work strives to solve this problem by applying a post-processing pipeline to models used by FL. In particular, the proposed work ranks the model by finding how fair they are by discovering and inspecting micro-Manifolds that cluster each neural model's latent knowledge. The produced work applies a completely unsupervised both model and data agnostic methodology that can be leveraged for general model fairness discovery. The proposed methodology is tested against a variety of benchmark DL architectures and in the FL environment, showing an average 8.75% increase in Federated model accuracy in comparison with similar work.

While the technology of Deep Learning (DL) is a powerful tool when properly trained for image analysis and classification applications, some factors for its optimization rely solely on the training data and their environment. In an effort to tackle the problem of knowledge bias created during the training process of a Deep Neural Network (DNN) and specifically Adversarial Networks for image augmentation, this work presents an entirely unsupervised methodology for discovering the unfairness level of Deep Learning (DL) models and in extend, its wrongly accumulated or biased classes. Fdi, the proposed evaluation metric for quantizing the level of unfairness of a model is introduced, along with the method of weighting the model’s knowledge and producing its weakest aspects in a data-agnostic way.

Traffic sign recognition (TSR) is a key aspect involved in the development of robust automated transportation systems. It inherently involves the task of traffic sign detection (TSD), which can be challenging due to traffic signs often being subject to deterioration or occlusion, caused by various environmental factors, or through actions of vandalism. Even though, notable advancements have been achieved in the areas of TSR and TSD, few studies have provided robust algorithms, able to be generalized in real-world applications. This mostly stems from the lack of an extensive traffic sign dataset, standardized for benchmarking purposes. In light of the aforementioned, this paper presents a novel traffic sign dataset, which consists of the Carla Traffic Sign Detection (CTSD), and the Carla Traffic Sign Recognition Dataset (CATERED), targeting the detection and recognition processes respectively. Using the proposed dataset for training and evaluation, a deep Auto-Encoder algorithm is presented, demonstrating high accuracy in detecting and recognizing the distorted traffic signs. Finally, the system is further extended to a federated learning environment, exemplifying its applicability in modern decentralized and interconnected architectures.

In recent years and with the advancement of IoT networks, malicious intrusions aiming at disrupting the services and getting access to confidential information in medical environments is ever progressing. To that end, this paper proposes a Federated Layered Architecture to be used in Medical Cyber-Physical Systems (MCPS) Networks that entails the creation of multiple aggregation layers to induce further security to the model training process. Moreover, two Deep Adversarial Neural Networks (GANs) are presented for use with data found in the MCPS environment. The evaluation of the presented work showed that the models trained in the Federated system have an increase in their ability to detect possible intrusions in the MCPS network than the commonly trained models.

The interconnected and heterogeneous nature of the next-generation Electrical Grid (EG), widely known as Smart Grid (SG), bring severe cybersecurity and privacy risks that can also raise domino effects against other Critical Infrastructures (CIs). In this paper, we present an Intrusion Detection System (IDS) specially designed for the SG environments that use Modbus/Transmission Control Protocol (TCP) and Distributed Network Protocol 3 (DNP3) protocols. The proposed IDS calledMENSA(anoMaly dEtection aNd claSsificAtion) adopts a novel Autoencoder-Generative Adversarial Network (GAN) architecture for (a) detecting operational anomalies and (b) classifying Modbus/TCP and DNP3 cyberattacks. In particular,MENSAcombines the aforementioned Deep Neural Networks (DNNs) in a common architecture, taking into account the adversarial loss and the reconstruction difference. The proposed IDS is validated in four real SG evaluation environments, namely (a) SG lab, (b) substation, (c) hydropower plant and (d) power plant, solving successfully an outlier detection (i.e., anomaly detection) problem as well as a challenging multiclass classification problem consisting of 14 classes (13 Modbus/TCP cyberattacks and normal instances). Furthermore,MENSAcan discriminate five cyberattacks against DNP3. The evaluation results demonstrate the efficiency ofMENSAcompared to other Machine Learning (ML) and Deep Learning (DL) methods in terms of Accuracy, False Positive Rate (FPR), True Positive Rate (TPR) and the F1 score.

Honeypots are powerful security tools, developed to shield commercial and industrial networks from malicious activity. Honeypots act as passive and interactive decoys in a network attracting malicious activity and securing the rest of the network entities. Since an increase in intrusions has been observed lately, more advanced security systems are necessary. In this paper a new method of adapting a honeypot system in a modern industrial network, employing the Modbus protocol, is introduced. In the presented NeuralPot honeypot, two distinct deep neural network implementations are utilized to adapt to network Modbus entities and clone them, actively confusing the intruders. The proposed deep neural networks and their generated data are then compared.