Search Results (104)

The convergence of Large Language Models (LLMs) and Internet of Things (IoT) systems has created a new class of intelligent applications across healthcare, industrial automation, smart cities, and connected homes. However, this integration introduces a complex and largely underexplored security landscape. LLMs deployed in IoT contexts face threats spanning both the AI and embedded systems domains, including prompt injection through sensor-driven inputs, model extraction from edge devices, data poisoning of IoT data streams, and privacy leakage through LLM-generated responses grounded in personal data. Simultaneously, LLMs are proving to be powerful tools for IoT security, with LLM-based intrusion detection systems achieving 95–99% accuracy on standard IoT datasets and LLM-driven threat intelligence outperforming traditional machine learning by significant margins. We systematically review 88 papers from IEEE, ACM, MDPI, and arXiv (2020–2025), providing: (1) a structured taxonomy of security threats targeting LLM-IoT systems, (2) a review of LLMs as security enablers for IoT, (3) an evaluation of privacy-preserving architectures including federated learning, differential privacy, homomorphic encryption, and trusted execution environments, (4) domain-specific security analysis across healthcare, industrial, smart home, smart grid, and vehicular IoT, and (5) a literature-based comparative analysis of LLM-based security systems. A central finding is the accuracy–efficiency–privacy trilemma: the model compression techniques needed to deploy LLMs on resource-constrained IoT devices can degrade security and even introduce new vulnerabilities. Our analysis provides researchers and practitioners with a structured understanding of both the risks and opportunities at the frontier of LLM-IoT security. Full article

Unmanned Aerial Vehicles (UAVs) are increasingly integrated into critical applications ranging from logistics and agriculture to defence and security operations, surveillance and emergency response. At the core of these systems lies the communication link between the UAV and its ground control station (GCS), which serves as the backbone for command, control and data exchange. However, communications links remain highly vulnerable to cyber-threats, including eavesdropping, signal falsification, radio frequency interference (RFI) and hijacking. These risks highlight the urgent need for secure communication protocols and effective defence mechanisms capable of protecting data confidentiality, integrity, availability and authentication. This study performs a comprehensive survey of secure UAV-GCS communication protocols and artificial intelligence (AI)-driven intrusion detection techniques. Initially, we review widely used communication protocols, examining their security features, vulnerabilities and existing countermeasures. Accordingly, a taxonomy of UAV-GCS security threats is proposed, structured around confidentiality, integrity, availability and authentication and map these threats to relevant attacks and defences. In parallel, our study examines state-of-the-art intrusion detection systems for UAVs, while particular emphasis is placed on emerging methods such as deep learning, federated learning, tiny machine learning and explainable AI, which hold promise for lightweight and real-time threat detection. The survey concludes by identifying open challenges, including resource constraints, lack of standardised secure protocols, scarcity of UAV-specific datasets and the evolving sophistication of attackers. Finally, we outline research directions for next-generation UAV architectures that integrate secure communication protocols with AI-based anomaly detection to achieve resilient and intelligent drone ecosystems. Full article

As Unmanned Aerial Vehicles (UAVs) become integral to critical infrastructure, ranging from precision agriculture to emergency disaster recovery, their security becomes a matter of systemic resilience. This paper provides a comprehensive thematic survey of the security landscape for unmanned devices, bridging the gap between low-level hardware vulnerabilities and high-level mission failures. We propose a multidimensional taxonomy that categorizes challenges into hardware roots of trust, swarm intelligence threats, and domain-specific applications. A primary focus is placed on the Resource–Security Paradox, where the energy cost of heavy cryptographic or AI defenses directly reduces flight endurance, creating a trade-off that adversaries exploit through battery-exhaustion attacks. Beyond standard threats, we analyze emerging risks in additive manufacturing supply chains, the “Sim-to-Real” gap in AI-driven perception, and the legal necessity of Digital Forensic Readiness (DFR) for post-incident attribution. Through a systematic review of defensive frameworks, including lightweight encryption, Mamba-KAN anomaly detection, and blockchain-anchored logging, we evaluate the effectiveness of current solutions against complex adversarial models. Finally, we identify critical research gaps, providing a roadmap for security-by-design in the next generation of critical infrastructure swarms. Full article

Background: This paper is a systematic review of 100 peer-reviewed articles (2015–2025) related to artificial intelligence (AI) applications in the auditing field, and includes machine learning, natural language processing, robotic process automation, and other AI methods. Purpose: The paper delves into the integration of these AI technologies into the audit workflow; empirical implications of these technologies on audit effectiveness; efficiency and quality; and technical, organizational, and regulatory obstacles that suggest more widespread adoption is still limited. Methods: Five large-scale databases and other sources were searched and selected using PRISMA; structured data were extracted, assessed in quality and narrative, and thematically analyzed. Results: The discussion indicates that machine learning-based anomaly detection and predictive analytics, document analysis through NLP, and automation through RPA are becoming part of planning, risk assessments, control tests, and substantive procedures/reporting, with improvements in detection capabilities, coverage and efficiency reported in various empirical and design science studies. The review also presents common architectural models of AI-enabled audit processes, including layered data and governance, model development and oversight, orchestration and automation, auditor-facing applications, and human-in-the-loop controls. Conclusions: The article proposes an AI-based audit workflow reference architecture and summarizes evidence on opportunities, threats, and implementation obstacles, highlighting gaps in longitudinal assessment, comparative evaluation of AI methods, and regulatory recommendations. The results have practical implications for auditors, standard-setters, and system designers seeking to revise the audit approach and regulations to enable AI-driven assurance. Full article

The rapid expansion of the Internet of Things (IoT) has opened resource-limited devices to novel physical threats, such as Side-Channel Attacks (SCAs) and Hardware Trojans (HTs). Traditional security mechanisms are often not capable of standing against such hardware-based attacks, specifically on low-power System-on-Chip (SoC) where static defenses can incur 2× to 3× overhead in silicon area and power. Herein, the gap between hardware security and embedded AI is compositionally formulated for discussion. We present a comprehensive survey of the current hardware threat landscape and analyze the emergence of “Secure-by-Design” paradigms, specifically focusing on the integration of Edge AI and TinyML as active, on-chip intrusion detection mechanisms. This review presents a critical analysis of trade-offs for running lightweight ML models on hardware by comparing state-of-the-art approaches. Our analysis highlights that optimized architectures, such as Mamba-Enhanced Convolutional Neural Networks (CNNs) and Gated Recurrent Unit (GRU), can achieve detection accuracies exceeding 99% against SCA and >92% against stealthy Hardware Trojans, while offering up to 75% lower power consumption compared to standard deep learning baselines. Finally, open challenges such as adversarial attacks on defense models are briefly discussed, and the focus is put on future directions toward constructing secure chips based on robust, AI-driven technology. Full article

The accumulation of space debris in near-Earth orbit, particularly in Low Earth Orbit (LEO), poses an increasing threat to satellite operations, communication infrastructures, and long-term space sustainability. As modern constellations expand and incorporate advanced satellite technologies, including sensing and wireless communications, artificial intelligence-of-things (AIoT), enabled payloads, and edge computing for on-orbit data processing, the risk profile grows. This paper reviews the current debris environment and existing sensing and monitoring techniques, highlights major collision events and deliberate debris-generating activities, and analyzes the role of both governmental and commercial satellite constellations in exacerbating and mitigating the challenges. Emerging space surveillance and tracking (SST) techniques, leveraging radar, optical sensors, and interferometric SAR for enhanced intelligence, surveillance, and reconnaissance (ISR), are highlighted alongside software-defined networking (SDN) approaches and cloud communication technology that enable coordinated debris-avoidance maneuvers. Key international regulatory frameworks, tracking architectures, and mitigation measures, including alignment with ISO 24113 standards, advanced TT&C capabilities, and evolving active debris removal technologies, are examined. The study emphasizes the necessity of a global, interoperable ecosystem that integrates AI/ML (artificial intelligence and machine learning)-driven situational awareness, secure SATCOM links with AJ/LPI/LPD (anti-jamming/low probability of interception/low probability of detection) characteristics, and collaborative protocols among space agencies, commercial operators, and regulatory bodies to ensure the sustainable use of orbital space for future generations. Full article

In today’s fast-changing digital environment, cyber-physical systems face escalating security challenges due to increasingly sophisticated cyberattacks. Artificial Intelligence (AI) has emerged as a powerful enabler of modern cyberattack detection, offering scalable, accurate, and adaptive solutions to counter dynamic threats. This paper provides a comprehensive review of recent advancements in AI-based cyberattack detection, focusing on Machine Learning (ML), Deep Learning (DL), Reinforcement Learning (RL), Federated Learning (FL), and emerging techniques such as generative AI, neuro-symbolic AI, swarm intelligence, lightweight AI, and quantum Computing. We evaluate the strengths and limitations of these approaches, highlighting their performance on benchmark datasets. The review discusses traditional signature-based Intrusion Detection Systems (IDS) and their limitations against novel attack patterns, contrasted with AI-driven anomaly-based and hybrid detection methods that improve detection rates for unknown and zero-day attacks. Key challenges, including computational costs, data quality, privacy concerns, and model interpretability, are analysed alongside the role of Explainable AI (XAI) in enhancing trust and transparency. The impact of computational resources, dataset representativeness, and evaluation metrics on AI model performance is also explored. Furthermore, we investigate the potential of lightweight AI for resource-constrained environments like IoT and edge devices, and quantum computing’s role in advancing detection efficiency and cryptographic security. The paper also draws attention to future research directions, particularly the development of up-to-date datasets, integration of hybrid quantum–classical models, and optimisation of asynchronous FL protocols to address evolving cybersecurity challenges. This study aims to inspire innovation in AI-driven cyberattack detection, fostering robust, interpretable, and efficient solutions for securing complex digital environments. Full article

Background: The outbreak and spreading of antimicrobial resistance (AMR) in a very short time has made most of the old-fashioned antibiotics ineffective, and thus new therapeutic substances have to be developed. The traditional methods of antibiotics discovery are defined by long periods of time, high levels of expenditure, and high rates of failure, which contributes to the necessity of new approaches. Artificial intelligence (AI) has become a disruptive technology that can be used to accelerate and optimize various steps of antibiotic discovery, such as target detection and virtual screening, new molecular design, and early-stage testing. Methods: This review provides an in-depth discussion of the role of AI methodologies in the form of machine learning, deep learning, natural language processing, and generative models in the discovery of small-molecule antibiotics and antimicrobial peptides (AMPs). The major areas that are discussed include virtual screening, pharmacokinetics optimization, resistance mechanism prediction, and AMPs design, which is accompanied by relevant case studies, including the AI-based discovery of Abaucin. Results: The article highlights how AI can be used in a synergistic relationship with synthetic biology, nanotechnology, and multi-omics data as a core component in the next generation of antimicrobial approaches, such as personalized therapy and predictive stewardship. The existing issues, i.e., the lack of data, bias in algorithms, and the translational divide between research and clinical use, are addressed, as well as suggested measures of responsible, collaborative, and ethical AI use. Conclusions: The combination of computational innovation with experimentation validation, AI-driven antibiotic discovery paves the way for a potent and scalable approach in addressing the rising threat of AMR. Full article

In the past decade, a growing number of cyberattacks have been reported, enabling unprecedented levels of personalization, automation, and deception. For instance, recent industry surveys have reported sharp increases in unique social engineering attacks within a single month of 2023, coinciding with the public release of ChatGPT-3.5. This trend highlights how Artificial Intelligence (AI)-powered phishing campaigns have become a significant threat to digital ecosystems. The present study provides an integrative analysis of how generative and deepfake technologies have reshaped the landscape of a Social Engineering (SE) attack, categorizing the main attack strategies and examining their psychological, technological, and ethical implications. In addition, to reviewing enabling technologies, our study conducts a comparative analysis of frameworks and analytical models across technical, empirical, and quantitative perspectives that model AI-driven SE operations and their defensive countermeasures. The convergence of these frameworks reveals three core capabilities—realism, personalization, and automation—that systematically amplify attack efficiency. Building on these insights, the study proposes the Unified Model for AI-Driven Social Engineering (UM-AISE), a conceptual framework that integrates these dimensions across the attack lifecycle and employs a theoretical Markov Decision Process (MDP) analysis. This formalization demonstrates how these capabilities can shift the attacker’s optimal strategy, offering a formal economic perspective distinct from empirical validation. Finally, the study discusses emerging ethical and regulatory challenges associated with AI-mediated deception, highlighting risks related to opacity, accountability, and large-scale manipulation. Taken together, these elements inform evolving approaches for detection, defense, and governance relevant to researchers, policymakers, and practitioners. Full article

Conventional Security Operations Center (SOC) solutions struggle to process representative operational alert streams efficiently and adapt to evolving cyber threats, highlighting the need for automated, intelligent threat detection and prioritization. This study presents a custom AI-driven framework that leverages unsupervised learning techniques to support SOC analysts in cyber threat detection, anomaly identification, and alert prioritization. The framework applies several clustering methods: HDBSCAN, DBSCAN, KMeans, and Gaussian Mixture Models for alert segmentation, and integrates anomaly detection using LOF and Isolation Forest, complemented by semi-supervised detection via One-Class SVM. Using textual, categorical, and numerical features from Wazuh alerts across three datasets, the system performs clustering and anomaly detection in the original high-dimensional feature space, with UMAP applied solely for two-dimensional visualization. HDBSCAN consistently produced well-separated clusters with effective noise detection, while, Isolation Forest evaluated via 10-fold cross-validation exhibited stable anomaly flagging and clear score separation across both cyber alert event data and synthetic threat injection experiments. Furthermore, the framework formulates a composite priority ranking that integrates anomaly severity, cluster rarity, and SOC contextual weighting, yielding actionable alert rankings. An interactive, analyst-centric dashboard enables SOC teams to explore top alerts, clusters, associated MITRE techniques, priority rankings, and geolocation data, providing insights while preserving human oversight. Overall, the proposed system transforms complex alert streams into structured insights, enhancing SOC situational awareness, decision support, and operational efficiency. Full article

Fractures are a leading cause of morbidity and mortality in Thoroughbred racehorses, posing a significant threat to their welfare and careers. This study introduces a deep learning model specifically designed to facilitate fracture detection in equine athletes. By leveraging extensive training on human fracture data and refining the model with equine imaging, it highlights the transformative potential of transfer learning across species and medical contexts. This approach is not limited to equine fractures but could be adapted for use in detecting injuries or conditions in other veterinary species and even human healthcare applications. A comprehensive databank of radiographs, sourced from public archives and equine hospitals, was curated to encompass diverse conditions (fracture and non-fracture), ensuring robust pattern recognition. The architecture integrates a Vision Transformer for global context modelling with a ResNet backbone and loss function to optimize local feature extraction and cross-species adaptability. The pipeline achieved 96.7% accuracy for modality classification, 97.2% accuracy for projection recognition, and fracture localization intersection over union values of 0.71–0.84 across equine datasets. This work bridges advancements in human and veterinary medicine, opening pathways for AI-driven solutions that extend beyond fractures, fostering improved diagnostic precision and broader applications across species (felines, canines, etc.). By integrating advanced imaging techniques with AI, this study aims to set a foundation for more comprehensive and versatile health monitoring systems. Full article

Global agriculture is facing significant threat from climate-driven abiotic stress, which endangers global food security by impacting crop performance and adaptation. However, traditional abiotic stress detection methods are often labor-intensive and lack precision and scalability. Efficient and reliable solutions are needed to meet rising global food demand. Recent advances in artificial intelligence (AI) offer highly accurate, non-invasive, and sustainable approaches for abiotic stress detection. This paper reviews the impact of AI, and specifically Machine and Deep Learning algorithms, coupled with synergistic technologies and diverse datasets (imaging techniques and Internet of Things (IoT) infrastructures), to identify unique signatures of abiotic stress, and assess its impact on growth and physiological performance. It contrasts with other reviews that address individual technologies and algorithms, while presenting abiotic stress detection as a secondary objective. We examined peer-reviewed journal articles on the use of AI in detecting abiotic stress. The reviewed literature was chosen based on the stress category, sensing mode, and AI technologies employed. A comparative analysis was performed to explore potential advancements of AI-based abiotic stress detection methods over traditional approaches and also challenges lied to the adoption of AI in agriculture for abiotic stress detection. Full article

AI-driven network security relies increasingly on Large Language Models (LLMs) to detect sophisticated threats; however, their deployment on resource-constrained edge devices is severely hindered by immense parameter scales. While unstructured pruning offers a theoretical reduction in model size, commodity Graphics Processing Unit (GPU) architectures fail to efficiently leverage element-wise sparsity due to the mismatch between fine-grained pruning patterns and the coarse-grained parallelism of Tensor Cores, leading to latency bottlenecks that compromise real-time analysis of high-volume security telemetry. To bridge this gap, we propose SPARTA (Sparse Parallel Architecture for Real-Time Threat Analysis), an algorithm–architecture co-design framework. Specifically, we integrate a hardware-based address remapping interface to enable flexible row-offset access. This mechanism facilitates a novel graph-based column vector merging strategy that aligns sparse data with Tensor Core parallelism, complemented by a pipelined execution scheme to mask decoding latencies. Evaluations on Llama2-7B and Llama2-13B benchmarks demonstrate that SPARTA achieves an average speedup of 2.35× compared to Flash-LLM, with peak speedups reaching 5.05×. These findings indicate that hardware-aware microarchitectural adaptations can effectively mitigate the penalties of unstructured sparsity, providing a viable pathway for efficient deployment in resource-constrained edge security. Full article

Wildfires are environmental hazards with severe ecological, social, and economic impacts. Wildfires devastate ecosystems, communities, and economies worldwide, with rising frequency and intensity driven by climate change, human activity, and environmental shifts. Analyzing wildfire insights such as detection, predictive patterns, and risk assessment enables proactive response and long-term prevention. However, most of the existing approaches have been focused on isolated processing of data, making it challenging to orchestrate cross-modal reasoning and transparency. This study proposed a novel orchestrator-based multi-agent system (MAS), with the aim of transforming multimodal environmental data into actionable intelligence for decision making. We designed a framework to utilize Large Multimodal Models (LMMs) augmented by structured prompt engineering and specialized Retrieval-Augmented Generation (RAG) pipelines to enable transparent and context-aware reasoning, providing a cutting-edge Visual Question Answering (VQA) system. It ingests diverse inputs like satellite imagery, sensor readings, weather data, and ground footage and then answers user queries. Validated by several public datasets, the system achieved a precision of 0.797 and an F1-score of 0.736. Thus, powered by Agentic AI, the proposed, human-centric solution for wildfire management, empowers firefighters, governments, and researchers to mitigate threats effectively. Full article

Modern cyber threats exhibit sophisticated, evasive behaviors that overwhelm traditional security systems, leading to prolonged periods of attackers remaining undetected. AI-driven autonomous agents promise a proactive solution but are themselves vulnerable to adversarial manipulation, including memory poisoning and behavioral exploitation. This paper introduces MAS-Hunt—a novel multi-agent system architecture for proactive threat hunting that operates directly on live telemetry within the Elastic Stack. MAS-Hunt employs a collaborative team of specialized AI agents to automate the threat hunting lifecycle while incorporating a security-first design with built-in defenses for memory integrity, cross-agent validation, and behavioral anomaly detection. Full article