Artificial Intelligence (AI) security research is promising and highly valuable in the current decade. In particular, deep neural network (DNN) security is receiving increased attention. Although DNNs have recently emerged as a prominent tool for addressing complex challenges across various machine learning (ML) tasks and DNNs stand out as the most widely employed, as well as holding a significant share in both research and industry, DNNs exhibit vulnerabilities to adversarial attacks where slight but intentional perturbations can deceive DNNs models. Consequently, several studies have proposed that DNNs are exposed to new attacks. Given the increasing prevalence of these attacks, researchers need to explore countermeasures that mitigate the associated risks and enhance the reliability of adapting DNNs to various critical applications. As a result, DNNs have been protected against adversarial attacks using a variety of defense mechanisms. Our primary focus is DNN as a foundational technology across all ML tasks. In this work, we comprehensively survey and present the latest research on DNN security based on various ML tasks, highlighting the adversarial attacks that cause DNNs to fail and the defense strategies that protect the DNNs. We review, explore, and elucidate the operational mechanisms of prevailing adversarial attacks and defense mechanisms applicable to all ML tasks utilizing DNN. Our review presents a detailed taxonomy for attacker and defender problems, providing a comprehensive and robust review of most state-of-the-art attacks and defenses in recent years. Additionally, we thoroughly examine the most recent systematic review concerning the measures used to evaluate the success of attack or defense methods. Finally, we address current challenges and open issues in this field and future research directions.

This study presents the design and analysis of a Quad-band perfect metamaterial absorber (PMMA) with five distinct absorption peaks, achieving absorption rates consistently above 96%. The absorption performance is thoroughly examined by varying the structural parameters to elucidate the mechanisms underlying the multi-band absorption. Additionally, we investigate the sensing capabilities of the absorber by analyzing its response to changes in the refractive index and thickness of the analyte. Sensitivity and figure of Merit (FOM) are utilized to evaluate the sensing performance. The sensor demonstrates refractive index and thickness sensitivities of 1.5 THz RIU⁻¹ and 0.5 THz RIU⁻¹, respectively, with corresponding FOMs of 97.424 and 91.633. These results surpass those of prior terahertz regime designs, highlighting the superior sensing capabilities of the proposed absorber. The proposed design is promising for sensing, filtering, and stealth technology applications.

Osteoporosis, a medical condition distinguished by the reduction of bone mineral density and the consequent degradation of bone structure, poses significant health scrutiny, especially in elderly individuals. The fractures and hospitalisations that occur worldwide are a direct consequence of socioeconomic conditions. Prompt intervention and therapy are crucial for the early stage osteoporosis diagnosis and the detection of bone fractures. Several established methods, including single-energy X-ray absorptiometry (SXA), dual-energy X-ray absorptiometry (DEXA), non-invasive magnetic resonance imaging (MRI), quantitative CT (QCT), quantitative ultrasonography (QUS), and others, are now being employed for diagnostic purposes. Despite the availability of these technologies, microwave sensing has emerged as a feasible approach for early identification of osteoporosis and bone fractures, owing to its numerous advantages. This review paper aims to provide a comprehensive summary of recent advancements in microwave sensing techniques specifically aimed at detecting osteoporosis and diagnosing bone fractures. Various measuring, sensing, and antenna scattering parameter post-processing approaches are classified and assessed for their effectiveness in identifying alterations in bone characteristics associated with osteoporosis. These techniques encompass both traditional non-invasive and invasive scanning procedures, along with more sophisticated machine learning-based prediction approaches. The reliability and efficiency of microwave sensing as a tool for the early detection of osteoporosis stage and bone fractures has been demonstrated by this work. This generates prospects for enhanced patient care and more intricate diagnosis and management strategies.

A metamaterial-incorporated high-gain and broadband dipole antenna is proposed for 5G mm-wave applications. The designed high refractive index metamaterial (HRIM) properties are presented in detail with supporting results. The proposed dipole antenna achieved broadband features, and the antenna gain increased significantly by incorporating HRIM in the electromagnetic (EM) wave propagation path. Besides, the EM wave aggregation engineering of utilizing the HRIM on the dipole antenna is analyzed using the electric field, magnetic field, and power flow distributions. Both conventional and HRIM-based dipole antenna (HRIMDA) were fabricated on thin (0.254 mm) Rogers RT5880 substrate material with a low dielectric constant of 2.2, where the noticeable gain enhancement by HRIM is observed. The measured results show the operational bandwidth (BW) from 23 to 38 GHz frequency, and the highest gain of 9.5 dBi is accomplished at 35 GHz frequency. Finally, a four-element MIMO configuration is numerically and experimentally analyzed where the isolation of the two conjugated MIMO elements is < − 20 dB. The MIMO parameters like envelop correlation coefficient (ECC) < 1 × 10^–3 and diversity gain (DG) value of > 9.9 were also achieved. Hence, the proposed HRIM base dipole antenna is a potential candidate for 5G mm-wave applications.

The dramatic growth of mobile data demand may impose a heavy traffic burden in indoor environments such that conventional radio frequency wireless networks might not be enough to ensure a high quality of service (QoS). Applications such as texting, 4k video streaming, and virtual reality have substantial differences in terms of data rate requirements. Visible light communication (VLC) has emerged recently as a complementary technology in heterogeneous networks, as it supports a high data rate and uses an unlicensed spectrum. In hybrid WiFi-VLC networks, users can be assigned to WiFi or VLC access points (AP) in downlink to maximize the minimum user data rate. In this paper, we propose an intelligent network selection that is capable of reducing network complexity and enhancing users’ QoS. A federated Q-learning (FQL) algorithm is proposed, where each VLC AP performs local Q-learning and updates the global model at the WiFi AP. A new local reward function is proposed to maximize user satisfaction with limited shared information. Furthermore, a deep neural network (DNN) is proposed to reduce the complexity of the FQL. The output of the DNN is adjusted to assign some users directly to WiFi or VLC and create an initial policy for the FQL. To quantify the improvements achieved, the proposed federated Q-learning assisted by knowledge transfer (FQL-KT) is compared against state-of-the-art benchmark approaches, such as centralized Q-learning (CQL), FQL, signal strength strategy (SSS), and exhaustive search. Numerical simulation results show that the proposed FQL-KT significantly outperformed the other approaches in terms of convergence speed, maximizing the minimum user data rate, fairness, and minimizing the outage probability.