Future Internet

17 pages, 1497 KB

Open AccessArticle

SPARTA: Sparse Parallel Architecture for Real-Time Threat Analysis for Lightweight Edge Network Defense

by Shi Li, Xiyun Mi, Lin Zhang and Ye Lu

Future Internet 2026, 18(2), 88; https://doi.org/10.3390/fi18020088 - 6 Feb 2026

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) [...] Read more.

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

(This article belongs to the Special Issue DDoS Attack Detection for Cyber–Physical Systems)

► Show Figures

Figure 1

21 pages, 43172 KB

Open AccessArticle

Location-Aware SDN-IDPS Framework for Real-Time DoS Mitigation in Vehicular Networks

by Aung Aung, Kuljaree Tantayakul and Adisak Intana

Future Internet 2026, 18(2), 87; https://doi.org/10.3390/fi18020087 - 6 Feb 2026

Abstract

Integrating Software-Defined Networking (SDN) to enhance mobility management in Vehicular Ad Hoc Networks (VANETs) comes with an additional critical risk. Because centralized controllers are single points of failure, they create the risk that the network will be subject to denial-of-service (DoS) attacks during [...] Read more.

Integrating Software-Defined Networking (SDN) to enhance mobility management in Vehicular Ad Hoc Networks (VANETs) comes with an additional critical risk. Because centralized controllers are single points of failure, they create the risk that the network will be subject to denial-of-service (DoS) attacks during handovers. Most Intrusion Detection and Prevention systems (IDPSs) do not adequately address these risks because they are topology-blind and have excessive processing layers. This article presents a novel Location-Aware SDN-IDPS Framework that employs a hierarchical defense approach to protect vehicular networks against volumetric attacks. This two-plane system operates with the first tier, which uses dynamic host-location mappings to drop spoofed traffic at the switch level (data plane). In contrast, the second tier analyzes confirmed traffic through a Suricata-based engine to identify and respond to complex flood attack patterns. The experimental results from the Mininet-WiFi testbed show that the system provides a significant improvement over the unprotected state, with controller CPU utilization reduced by up to 18 times (from 9.0% to below 0.5%). In addition, the system provides a 2.3 s guaranteed recovery time, service continuity, successful microsecond-level mitigation time, and a packet delivery ratio (PDR) of 99.73% for legitimate safety messages. In control-plane stress testing, the proposed location-aware logic improved throughput stability by approximately 76.26% compared to the baseline. These findings confirm that offloading anti-spoofing logic to the network edge significantly enhances resilience without compromising performance in safety-critical vehicular environments. Full article

(This article belongs to the Special Issue Software-Defined Networking (SDN) and Network Function Virtualization (NFV) for a Hyperconnected World)

► Show Figures

Figure 1

20 pages, 682 KB

Open AccessArticle

Semantic Search for System Dynamics Models Using Vector Embeddings in a Cloud Microservices Environment

by Pavel Kyurkchiev, Anton Iliev and Nikolay Kyurkchiev

Future Internet 2026, 18(2), 86; https://doi.org/10.3390/fi18020086 - 5 Feb 2026

Abstract

Efficient retrieval of mathematical and structural similarities in System Dynamics models remains a significant challenge for traditional lexical systems, which often fail to capture the contextual dependencies of simulation processes. This paper presents an architectural approach and implementation of a semantic search module [...] Read more.

Efficient retrieval of mathematical and structural similarities in System Dynamics models remains a significant challenge for traditional lexical systems, which often fail to capture the contextual dependencies of simulation processes. This paper presents an architectural approach and implementation of a semantic search module integrated into an existing cloud-based modeling and simulation system. The proposed method employs a strategy for serializing graph structures into textual descriptions, followed by the generation of vector embeddings via local ONNX inference and indexing within a vector database (Qdrant). Experimental validation performed on a diverse corpus of complex dynamic models, compares the proposed approach against traditional information retrieval methods (Full-Text Search, Keyword Search in PostgreSQL, and Apache Lucene with Standard and BM25 scoring). The results demonstrate the distinct advantage of semantic search, achieving high precision (over 90%) within the scope of the evaluated corpus and effectively eliminating information noise. In comparison, keyword search exhibited only 24.8% precision with a significant rate of false positives, while standard full-text analysis failed to identify relevant models for complex conceptual queries (0 results). Despite a recorded increase in latency (~2 s), the study proves that the vector-based approach is a significantly more robust solution for detecting hidden semantic connections in mathematical model databases, providing a foundation for future developments toward multi-vector indexing strategies. Full article

(This article belongs to the Special Issue Intelligent Agents and Their Application)

► Show Figures

Figure 1

24 pages, 2506 KB

Open AccessArticle

CEVD: Cluster-Based Ensemble Learning for Cross-Project Vulnerability Detection

by Yang Cao, Yunwei Dong and Jie Liu

Future Internet 2026, 18(2), 85; https://doi.org/10.3390/fi18020085 - 5 Feb 2026

Abstract

Deep learning has become an important approach for automated software vulnerability detection. However, due to domain shift, existing models often suffer from significant performance degradation when applied to unseen projects. To address this issue, prior studies have widely adopted Domain Adaptation (DA) techniques [...] Read more.

Deep learning has become an important approach for automated software vulnerability detection. However, due to domain shift, existing models often suffer from significant performance degradation when applied to unseen projects. To address this issue, prior studies have widely adopted Domain Adaptation (DA) techniques to improve cross-project generalization. Nevertheless, these methods typically rely on the implicit “project-as-domain” assumption and require access to target project data during training, which limits their applicability in practice. To overcome these limitations, this paper proposes a vulnerability detection framework that combines semantic clustering with ensemble-based Domain Generalization (DG), termed Cluster-based Ensemble Learning for Vulnerability Detection (CEVD). CEVD first performs unsupervised clustering on code semantic embeddings to automatically automatically identify latent semantic structures that transcend project boundaries, constructing pseudo-domains with intra-domain homogeneity. A soft domain labeling strategy is further introduced to model the membership of samples in multiple pseudo-domains, preserving semantic overlap across boundaries. Building upon this, CEVD employs an ensemble learning framework that jointly trains multiple expert models and a domain classifier. The predictions of these experts are dynamically fused based on the weights generated by the domain classifier, enabling effective vulnerability detection on unseen projects without requiring access to target data. Extensive experiments on real-world datasets demonstrate that CEVD consistently outperforms state-of-the-art baselines across different pre-trained backbone models. This work demonstrates the effectiveness of semantic structure mining in capturing latent domains and offers a practical solution for improving generalization in cross-project vulnerability detection. Full article

(This article belongs to the Special Issue Security of Computer System and Network)

► Show Figures

Figure 1

27 pages, 1470 KB

Open AccessArticle

User Perceptions of Virtual Consultations and Artificial Intelligence Assistance: A Mixed Methods Study

by Pranavsingh Dhunnoo, Karen McGuigan, Vicky O’Rourke, Bertalan Meskó and Michael McCann

Future Internet 2026, 18(2), 84; https://doi.org/10.3390/fi18020084 - 4 Feb 2026

Abstract

Background: In recent years, virtual consultations have emerged as a crucial approach for continuity of chronic care provision, indicating a promising avenue for the future of smart healthcare systems. However, reversions to in-person care highlight persistent limitations, despite notable advantages of remote modalities. [...] Read more.

Background: In recent years, virtual consultations have emerged as a crucial approach for continuity of chronic care provision, indicating a promising avenue for the future of smart healthcare systems. However, reversions to in-person care highlight persistent limitations, despite notable advantages of remote modalities. In parallel, recent developments in artificial intelligence (AI) indicate the potential to enhance remote chronic care, but user perceptions of such assistance and the corresponding human factors remain underexplored. Objective: This mixed methods study aims to better understand the virtual consultation experiences and attitudes toward AI-assisted tools in remote care among patients with noncommunicable chronic conditions and their healthcare professionals (HCPs). It conducts an in-depth examination of the associated human–computer interaction and usability elements of virtual consultations and of potential AI assistance. Methods: Public and Patient Involvement was integrated to run pilots and refine documentations. Semi-structured interviews with patients (n = 10), focus groups with HCPs (n = 15), and an online survey (n = 83) were conducted. Qualitative data was analysed through a reflexive thematic approach. The survey comprised the Telehealth Usability Questionnaire (TUQ) and bespoke items on user AI views, and the data was used to triangulate the qualitative findings. Nonparametric Kruskal–Wallis tests and ε² effect sizes compared TUQ and AI views scores between current and former virtual consultation user groups. Results: Seven themes emerged from the qualitative data, which were supported by the quantitative findings. The statistical analyses resulted in a mean TUQ total score of 90.6 (SD = 15.0), which indicates high usability and user satisfaction; however, they failed to detect a difference between groups (p > 0.05; ε² = 0.002–0.032). There was a clear preference for hybrid models, while a lack of empathy was identified during remote interactions. While a notable proportion of users indicated a literacy gap towards AI use in healthcare settings, they expressed cautious openness towards AI assistance, contingent upon transparency, human oversight, and data integrity; indicating a potential gap between competence to judge the technology and willingness to use it. Significant differences in views on AI assistance across groups failed to be detected (p > 0.05; ε² = 0.005–0.065). Conclusions: Virtual consultations for chronic conditions are widely usable and acceptable, particularly through hybrid approaches. Addressing empathic engagement, holistic patient status, and transparent AI integration can enhance clinical quality and user experiences during remote interactions. However, the low statistical power and failure to detect a difference between groups (likely due to the small sample size) indicate the need for caution when interpreting the quantitative findings. There is also the implicit need to address potential AI literacy gap among users, indicating the need for robust safeguard measures. This study has also identified evidence-based assistive AI features that can potentially enhance virtual consultations. These insights can inform the co-design of evidence-based virtual care platforms, policies and supportive AI tools to sustain remote chronic care delivery. Full article

(This article belongs to the Special Issue Artificial Intelligence (AI) in Healthcare: Technologies, Applications, Challenges)

► Show Figures

Graphical abstract

69 pages, 30976 KB

Open AccessReview

Next-Gen Explainable AI (XAI) for Federated and Distributed Internet of Things Systems: A State-of-the-Art Survey

by Aristeidis Karras, Anastasios Giannaros, Natalia Amasiadi and Christos Karras

Future Internet 2026, 18(2), 83; https://doi.org/10.3390/fi18020083 - 4 Feb 2026

Abstract

Background: Explainable Artificial Intelligence (XAI) is deployed in Internet of Things (IoT) ecosystems for smart cities and precision agriculture, where opaque models can compromise trust, accountability, and regulatory compliance. Objective: This survey investigates how XAI is currently integrated into distributed and federated IoT [...] Read more.

Background: Explainable Artificial Intelligence (XAI) is deployed in Internet of Things (IoT) ecosystems for smart cities and precision agriculture, where opaque models can compromise trust, accountability, and regulatory compliance. Objective: This survey investigates how XAI is currently integrated into distributed and federated IoT architectures and identifies systematic gaps in evaluation under real-world resource constraints. Methods: A structured search across IEEE Xplore, ACM Digital Library, ScienceDirect, SpringerLink, and Google Scholar targeted publications related to XAI, IoT, edge/fog computing, smart cities, smart agriculture, and federated learning. Relevant peer-reviewed works were synthesized along three dimensions: deployment tier (device, edge/fog, cloud), explanation scope (local vs. global), and validation methodology. Results: The analysis reveals a persistent resource–interpretability gap: computationally intensive explainers are frequently applied on constrained edge and federated platforms without explicitly accounting for latency, memory footprint, or energy consumption. Only a minority of studies quantify privacy–utility effects or address causal attribution in sensor-rich environments, limiting the reliability of explanations in safety- and mission-critical IoT applications. Contribution: To address these shortcomings, the survey introduces a hardware-centric evaluation framework with the Computational Complexity Score (CCS), Memory Footprint Ratio (MFR), and Privacy–Utility Trade-off (PUT) metrics and proposes a hierarchical IoT–XAI reference architecture, together with the conceptual Internet of Things Interpretability Evaluation Standard (IOTIES) for cross-domain assessment. Conclusions: The findings indicate that IoT–XAI research must shift from accuracy-only reporting to lightweight, model-agnostic, and privacy-aware explanation pipelines that are explicitly budgeted for edge resources and aligned with the needs of heterogeneous stakeholders in smart city and agricultural deployments. Full article

(This article belongs to the Special Issue Human-Centric Explainability in Large-Scale IoT and AI Systems)

► Show Figures

Graphical abstract

22 pages, 3280 KB

Open AccessSystematic Review

From IoT to AIoT: Evolving Agricultural Systems Through Intelligent Connectivity in Low-Income Countries

by Selain K. Kasereka, Alidor M. Mbayandjambe, Ibsen G. Bazie, Heriol F. Zeufack, Okurwoth V. Ocama, Esteve Hassan, Kyandoghere Kyamakya and Tasho Tashev

Future Internet 2026, 18(2), 82; https://doi.org/10.3390/fi18020082 - 3 Feb 2026

Abstract

The convergence of Artificial Intelligence and the Internet of Things has given rise to the Artificial Intelligence of Things (AIoT), which enables connected systems to operate with greater autonomy, adaptability, and contextual awareness. In agriculture, this evolution supports precision farming, improves resource allocation, [...] Read more.

The convergence of Artificial Intelligence and the Internet of Things has given rise to the Artificial Intelligence of Things (AIoT), which enables connected systems to operate with greater autonomy, adaptability, and contextual awareness. In agriculture, this evolution supports precision farming, improves resource allocation, and strengthens climate resilience by enhancing the capacity of farming systems to anticipate, absorb, and recover from environmental shocks. This review provides a structured synthesis of the transition from IoT-based monitoring to AIoT-driven intelligent agriculture and examines key applications such as smart irrigation, pest and disease detection, soil and crop health assessment, yield prediction, and livestock management. To ensure methodological rigor and transparency, this study follows the PRISMA 2020 guidelines for systematic literature reviews. A comprehensive search and multi-stage screening procedure was conducted across major scholarly repositories, resulting in a curated selection of studies published between 2018 and 2025. These sources were analyzed thematically to identify technological enablers, implementation barriers, and contextual factors affecting adoption particularly within low-income countries where infrastructural constraints, limited digital capacity, and economic disparities shape AIoT deployment. Building on these insights, the article proposes an AIoT architecture tailored to resource-constrained agricultural environments. The architecture integrates sensing technologies, connectivity layers, edge intelligence, data processing pipelines, and decision-support mechanisms, and is supported by governance, data stewardship, and capacity-building frameworks. By combining systematic evidence with conceptual analysis, this review offers a comprehensive perspective on the transformative potential of AIoT in advancing sustainable, inclusive, and intelligent food production systems. Full article

(This article belongs to the Special Issue Machine Learning and Internet of Things in Industry 4.0)

► Show Figures

Figure 1

23 pages, 871 KB

Open AccessArticle

TLOA: A Power-Adaptive Algorithm Based on Air–Ground Cooperative Jamming

by Wenpeng Wu, Zhenhua Wei, Haiyang You, Zhaoguang Zhang, Chenxi Li, Jianwei Zhan and Shan Zhao

Future Internet 2026, 18(2), 81; https://doi.org/10.3390/fi18020081 - 2 Feb 2026

Abstract

Air–ground joint jamming enables three-dimensional, distributed jamming configurations, making it effective against air–ground communication networks with complex, dynamically adjustable links. Once the jamming layout is fixed, dynamic jamming power scheduling becomes essential to conserve energy and prolong jamming duration. However, existing methods suffer [...] Read more.

Air–ground joint jamming enables three-dimensional, distributed jamming configurations, making it effective against air–ground communication networks with complex, dynamically adjustable links. Once the jamming layout is fixed, dynamic jamming power scheduling becomes essential to conserve energy and prolong jamming duration. However, existing methods suffer from poor applicability in such scenarios, primarily due to their sparse deployment and adversarial nature. To address this limitation, this paper develops a set of mathematical models and a dedicated algorithm for air–ground communication countermeasures. Specifically, we (1) randomly select communication nodes to determine the jammer operation sequence; (2) schedule the number of active jammers by sorting transmission path losses in ascending order; and (3) estimate jamming effects using electromagnetic wave propagation characteristics to adjust jamming power dynamically. This approach formally converts the original dynamic, stochastic jamming resource scheduling problem into a static, deterministic one via cognitive certainty of dynamic parameters and deterministic modeling of stochastic factors—enabling rapid adaptation to unknown, dynamic communication power strategies and resolving the coordination challenge in air–ground joint jamming. Experimental results demonstrate that the proposed Transmission Loss Ordering Algorithm (TLOA) extends the system operating duration by up to 41.6% compared to benchmark methods (e.g., genetic algorithm). Full article

(This article belongs to the Special Issue Adversarial Attacks and Cyber Security)

► Show Figures

Graphical abstract

26 pages, 2695 KB

Open AccessArticle

LoRa/LoRaWAN Time Synchronization: A Comprehensive Analysis, Performance Evaluation, and Compensation of Frame Timestamping

by Stefano Rinaldi, Elia Mondini, Paolo Ferrari, Alessandra Flammini and Emiliano Sisinni

Future Internet 2026, 18(2), 80; https://doi.org/10.3390/fi18020080 - 2 Feb 2026

Abstract

This paper examines precise timestamping of LoRaWAN messages (particularly beacons) to enable wide-area synchronization for end devices without GNSS. The need for accuracy demands hardware-level timestamping architectures, possibly using time-domain cross-correlation (matched filtering) against internally generated chirp references. Focusing on Time-of-Arrival (TOA [...] Read more.

This paper examines precise timestamping of LoRaWAN messages (particularly beacons) to enable wide-area synchronization for end devices without GNSS. The need for accuracy demands hardware-level timestamping architectures, possibly using time-domain cross-correlation (matched filtering) against internally generated chirp references. Focusing on Time-of-Arrival (TOA) estimation from raw IQ samples, the authors analyze effects of non-idealities—additive white Gaussian noise (AWGN), Carrier Frequency Offset (CFO), Sampling Phase and Frequency Offset (SPO and SFO, respectively), and radio parameters such as spreading factor (SF) and sampling rate of the baseband signals. A MATLAB (R2020) simulation mimics preamble detection and Start-of-Frame Delimiter (SFD) timestamping while sweeping SF (7, 9, 12), sampling rates (0.25–10 MSa/s), SNR (−20 to +20 dB), and CFO/SFO offsets (−10–10 ppm frequency deviation). Errors are evaluated in terms of mean and dispersion, the latter represented by the P95–P5 range metric. Results show that oversampling not only improves temporal resolution, but sub-microsecond error dispersion can be achieved with high sampling rates in favorable SNR and SF cases. Indeed, SPO and SNR greatly contribute to error dispersion. On the other hand, higher SF values increase correlation robustness at the cost of longer chirps, making SFO a dominant error source; ±10 ppm SFO can induce roughly ±3 μs SFD bias for SF12. CFO largely cancels after up-/down-chirp averaging. As a concluding remark, matched-filter hardware timestamping can ensure sub-μs errors thanks to oversampling but requires SFO compensation for accurate real-world synchronization in practice. Full article

(This article belongs to the Special Issue Edge and Fog Computing for the Internet of Things, 2nd Edition)

► Show Figures

Graphical abstract

26 pages, 1243 KB

Open AccessArticle

Trajectory Planning for Autonomous Underwater Vehicles in Uneven Environments: A Survey of Coverage and Sensor Data Collection Methods

by Talal S. Almuzaini and Andrey V. Savkin

Future Internet 2026, 18(2), 79; https://doi.org/10.3390/fi18020079 - 2 Feb 2026

Abstract

Autonomous Underwater Vehicles (AUVs) play a central role in marine observation, inspection, and monitoring missions, where effective trajectory planning is essential for ensuring safe operation, reliable sensing, and efficient data transfer. In realistic underwater environments, uneven seafloor geometry, limited acoustic communication, navigation uncertainty, [...] Read more.

Autonomous Underwater Vehicles (AUVs) play a central role in marine observation, inspection, and monitoring missions, where effective trajectory planning is essential for ensuring safe operation, reliable sensing, and efficient data transfer. In realistic underwater environments, uneven seafloor geometry, limited acoustic communication, navigation uncertainty, and sensing visibility constraints significantly influence mission performance and challenge classical planar planning formulations. This survey reviews trajectory planning methods for AUVs operating in uneven environments, with a focus on two major classes of underwater sensing missions: underwater area coverage using onboard sensors and underwater sensor data collection within underwater acoustic sensor networks (UASNs) supporting the Internet of Underwater Things (IoUT). For area coverage, the survey examines the progression from classical planar coverage strategies to terrain-aware, occlusion-aware, multi-AUV, and online planning frameworks designed to address uneven terrain and sensing visibility. For underwater sensor data collection, it reviews mobile sink-based trajectory planning strategies, including energy-aware, channel-aware, and information-based formulations based on metrics such as Age of Information (AoI) and Value of Information (VoI), as well as cooperative architectures involving unmanned surface vehicles (USVs). By synthesizing these two bodies of literature, the survey clarifies current capabilities and limitations of trajectory planning methods for AUVs operating in uneven underwater environments. Full article

(This article belongs to the Special Issue Navigation, Deployment and Control of Intelligent Unmanned Vehicles)

► Show Figures

Figure 1

29 pages, 5294 KB

Open AccessArticle

Building a Regional Platform for Monitoring Air Quality

by Stanimir Nedyalkov Stoyanov, Boyan Lyubomirov Belichev, Veneta Veselinova Tabakova-Komsalova, Yordan Georgiev Todorov, Angel Atanasov Golev, Georgi Kostadinov Maglizhanov, Ivan Stanimirov Stoyanov and Asya Georgieva Stoyanova-Doycheva

Future Internet 2026, 18(2), 78; https://doi.org/10.3390/fi18020078 - 2 Feb 2026

Abstract

This paper presents PLAM (Plovdiv Air Monitoring)—a regional multi-agent platform for air quality monitoring, semantic reasoning, and forecasting. The platform uses a hybrid architecture that combines two types of intelligent agents: classic BDI (Belief-Desire-Intention) agents for complex, goal-oriented behavior and planning, and ReAct [...] Read more.

This paper presents PLAM (Plovdiv Air Monitoring)—a regional multi-agent platform for air quality monitoring, semantic reasoning, and forecasting. The platform uses a hybrid architecture that combines two types of intelligent agents: classic BDI (Belief-Desire-Intention) agents for complex, goal-oriented behavior and planning, and ReAct agents based on large language models (LLM) for quick response, analysis, and interaction with users. The system integrates data from heterogeneous sources, including local IoT sensor networks and public external services, enriching it with a specialized OWL ontology of environmental norms. Based on this data, the platform performs comparative analysis, detection of anomalies and inconsistencies between measurements, as well as predictions using machine learning models. The results are visualized and presented to users via a web interface and mobile application, including personalized alerts and recommendations. The architecture demonstrates essential properties of an intelligent agent such as autonomy, proactivity, reactivity, and social capabilities. The implementation and testing in the city of Plovdiv demonstrate the system’s ability to provide a more objective and comprehensive assessment of air quality, revealing significant differences between measurements from different institutions. The platform offers a modular and adaptive design, making it applicable to other regions, and outlines future development directions, such as creating a specialized small language model and expanding sensor capabilities. Full article

(This article belongs to the Special Issue Intelligent Agents and Their Application)

► Show Figures

Graphical abstract

19 pages, 21358 KB

Open AccessArticle

Aerial Image Analysis: When LLMs Assist (And When Not)

by Salvatore Calcagno, Erika Scaletta, Emiliano Tramontana and Gabriella Verga

Future Internet 2026, 18(2), 77; https://doi.org/10.3390/fi18020077 - 1 Feb 2026

Abstract

Large language models (LLMs) have shown remarkable results when tasked with the analysis and production of texts or images and for captioning images. Aerial images differ from other images since they exhibit many natural objects that have a highly variable color range and [...] Read more.

Large language models (LLMs) have shown remarkable results when tasked with the analysis and production of texts or images and for captioning images. Aerial images differ from other images since they exhibit many natural objects that have a highly variable color range and no clear contours. This paper reports to what extent an LLM, i.e., Llama-4, can be tasked with the identification and captioning in aerial images of natural objects, such as tree categories, uncultivated land, and some man-made objects, such as roads. This valuable automation is needed to scan large areas and detect the parts for which a sudden maintenance or an emergency intervention is due. Tests on the chosen LLM were performed against a custom image dataset built to overcome the limited availability of such a domain-specific aerial image set. To evaluate the identification and captioning results, the accuracy, precision and recall metrics were computed. The results given by a cutting-edge variant of Llama-4, namely Maverick, reveal its strengths and weaknesses in this context. Although it is remarkable that an out-of-the-box tool can give assistance in such a complex observation and detection task, substantial progress is needed for such a model to improve accuracy and constitute a reliable support, as accuracy is at most 58.6% and recall is at most 56.1%. Full article

39 pages, 2037 KB

Open AccessReview

Research on Intelligent Resource Management Solutions for Green Cloud Computing

by Amirmohammad Parhizkar, Ehsan Arianyan and Pejman Goudarzi

Future Internet 2026, 18(2), 76; https://doi.org/10.3390/fi18020076 - 1 Feb 2026

Abstract

Cloud computing utilization has experienced progressive expansion over the last decade, which has raised concerns and challenges regarding efficient resource allocation and energy efficiency. The burgeoning increase in the number of cloud computing users and their data exacerbates the difficulty of resolving these [...] Read more.

Cloud computing utilization has experienced progressive expansion over the last decade, which has raised concerns and challenges regarding efficient resource allocation and energy efficiency. The burgeoning increase in the number of cloud computing users and their data exacerbates the difficulty of resolving these challenges using conventional methods. Thus, utilizing intelligent approaches is indispensable. Among the most recent intelligent methods, artificial intelligence-based techniques have gained prominence across numerous research domains, including cloud resource management. Through a literature review aimed at analyzing existing studies addressing the open challenges of cloud computing, we have identified some gaps that are presented in this paper. Moreover, this paper presents a survey on cloud resource management solutions spanning from 2018 to 2025, with a focus on the papers that utilized intelligent methodologies for green computing. More specifically, this study shed light on the prevailing challenges in the field concerning methods, research areas, metrics, tools, and datasets. Furthermore, it provides a clear classification of methods, research areas, and metrics. Full article

(This article belongs to the Special Issue Cloud/Edge Computing for Next-Generation Networks: Architecture and Applications)

► Show Figures

Figure 1

32 pages, 2836 KB

Open AccessArticle

Towards Trustworthy AI Agents in Geriatric Medicine: A Secure and Assistive Architectural Blueprint

by Elena-Anca Paraschiv, Adrian Victor Vevera, Carmen Elena Cîrnu, Lidia Băjenaru, Andreea Dinu and Gabriel Ioan Prada

Future Internet 2026, 18(2), 75; https://doi.org/10.3390/fi18020075 - 1 Feb 2026

Abstract

As artificial intelligence (AI) continues to expand across clinical environments, healthcare is transitioning from static decision-support tools to dynamic, autonomous agents capable of reasoning, coordination, and continuous interaction. In the context of geriatric medicine, a field characterized by multimorbidity, cognitive decline, and the [...] Read more.

As artificial intelligence (AI) continues to expand across clinical environments, healthcare is transitioning from static decision-support tools to dynamic, autonomous agents capable of reasoning, coordination, and continuous interaction. In the context of geriatric medicine, a field characterized by multimorbidity, cognitive decline, and the need for long-term personalized care, this evolution opens new frontiers for delivering adaptive, assistive, and trustworthy digital support. However, the autonomy and interconnectivity of these systems introduce heightened cybersecurity and ethical challenges. This paper presents a Secure Agentic AI Architecture (SAAA) tailored to the unique demands of geriatric healthcare. The architecture is designed around seven layers, grouped into five functional domains (cognitive, coordination, security, oversight, governance) to ensure modularity, interoperability, explainability, and robust protection of sensitive health data. A review of current AI agent implementations highlights limitations in security, transparency, and regulatory alignment, especially in multi-agent clinical settings. The proposed framework is illustrated through a practical use case involving home-based care for elderly patients with chronic conditions, where AI agents manage medication adherence, monitor vital signs, and support clinician communication. The architecture’s flexibility is further demonstrated through its application in perioperative care coordination, underscoring its potential across diverse clinical domains. By embedding trust, accountability, and security into the design of agentic systems, this approach aims to advance the safe and ethical integration of AI into aging-focused healthcare environments. Full article

(This article belongs to the Special Issue Intelligent Agents and Their Application)

► Show Figures

Graphical abstract

35 pages, 8093 KB

Open AccessArticle

DACCA: Distributed Adaptive Cloud Continuum Architecture

by Nektarios Deligiannakis, Vassilis Papataxiarhis, Michalis Loukeris, Stathes Hadjiefthymiades, Marios Touloupou, Syed Mafooq Ul Hassan, Herodotos Herodotou, Thanasis Moustakas, Emmanouil Bampis, Konstantinos Ioannidis, Iakovos T. Michailidis, Stefanos Vrochidis, Elias Kosmatopoulos, Francisco Javier Romero Martínez, Rafael Marín Pérez, Amr Mousa, Jacopo Castellini and Pablo Strasser

Future Internet 2026, 18(2), 74; https://doi.org/10.3390/fi18020074 - 1 Feb 2026

Abstract

Recently, the need for unified orchestration frameworks that can manage extremely heterogeneous, distributed, and resource-constrained environments has emerged due to the rapid development of cloud, edge, and IoT computing. Kubernetes and other traditional cloud-native orchestration systems are not built to facilitate autonomous, decentralized [...] Read more.

Recently, the need for unified orchestration frameworks that can manage extremely heterogeneous, distributed, and resource-constrained environments has emerged due to the rapid development of cloud, edge, and IoT computing. Kubernetes and other traditional cloud-native orchestration systems are not built to facilitate autonomous, decentralized decision-making across the computing continuum or to seamlessly integrate non-container-native devices. This paper presents the Distributed Adaptive Cloud Continuum Architecture (DACCA), a Kubernetes-native architecture that extends orchestration beyond the data center to encompass edge and Internet of Things infrastructures. Decentralized self-awareness and swarm formation are supported for adaptive and resilient operation, a resource and application abstraction layer is established for uniform resource representation, and a Distributed and Adaptive Resource Optimization (DARO) framework based on multi-agent reinforcement learning is integrated for intelligent scheduling in the proposed architecture. Verifiable identity, access control, and tamper-proof data exchange across heterogeneous domains are further ensured by a zero-trust security framework based on distributed ledger technology. When combined, these elements enable increasingly autonomous workload orchestration, trading centralized control for adaptive, decentralized operation with enhanced interoperability, scalability, and trust. Thus, the proposed architecture enables self-managing and context-aware orchestration systems that support next-generation AI-driven distributed applications across the entire computing continuum. Full article

(This article belongs to the Special Issue Scalable and Distributed Cloud Continuum Orchestration for Next-Generation IoT Applications: Latest Advances and Prospects—2nd Edition)

18 pages, 5241 KB

Open AccessViewpoint

The Generative AI Paradox: GenAI and the Erosion of Trust, the Corrosion of Information Verification, and the Demise of Truth

by Emilio Ferrara

Future Internet 2026, 18(2), 73; https://doi.org/10.3390/fi18020073 - 1 Feb 2026

Abstract

Generative AI (GenAI) now produces text, images, audio, and video that can be perceptually convincing at scale and at negligible marginal cost. While public debate often frames the associated harms as “deepfakes” or incremental extensions of misinformation and fraud, this view misses a [...] Read more.

Generative AI (GenAI) now produces text, images, audio, and video that can be perceptually convincing at scale and at negligible marginal cost. While public debate often frames the associated harms as “deepfakes” or incremental extensions of misinformation and fraud, this view misses a broader socio-technical shift: GenAI enables synthetic realities—coherent, interactive, and potentially personalized information environments in which content, identity, and social interaction are jointly manufactured and mutually reinforcing. We argue that the most consequential risk is not merely the production of isolated synthetic artifacts, but the progressive erosion of shared epistemic ground and institutional verification practices as synthetic content, synthetic identity, and synthetic interaction become easy to generate and hard to audit. This paper (i) formalizes synthetic reality as a layered stack (content, identity, interaction, institutions), (ii) expands a taxonomy of GenAI harms spanning personal, economic, informational, and socio-technical risks, (iii) articulates the qualitative shifts introduced by GenAI (cost collapse, throughput, customization, micro-segmentation, provenance gaps, and trust erosion), and (iv) synthesizes recent risk realizations (2023–2025) into a compact case bank illustrating how these mechanisms manifest in fraud, elections, harassment, documentation, and supply-chain compromise. We then propose a mitigation stack that treats provenance infrastructure, platform governance, institutional workflow redesign, and public resilience as complementary rather than substitutable, and outline a research agenda focused on measuring epistemic security. We conclude with the Generative AI Paradox: as synthetic media becomes ubiquitous, societies may rationally discount digital evidence altogether, raising the cost of truth for everyday life and for democratic and economic institutions. Full article

(This article belongs to the Special Issue 2024 and 2025 Feature Papers from Future Internet’s Editorial Board Members)

► Show Figures

Figure 1

38 pages, 2357 KB

Open AccessArticle

Aris-RPL: A Multi-Objective Reinforcement Learning Framework for Adaptive and Load-Balanced Routing in IoT Networks

by Najim Halloum, Ali Ahmadi and Yousef Darmani

Future Internet 2026, 18(2), 72; https://doi.org/10.3390/fi18020072 - 31 Jan 2026

Abstract

The fast-paced utilization of innovative Internet of Things (IoT) applications emphasizes the critical role that routing protocols play in designing an efficient communication system between network nodes. In this context, the lack of adaptive routing mechanisms in the standard Routing Protocol for Low-power [...] Read more.

The fast-paced utilization of innovative Internet of Things (IoT) applications emphasizes the critical role that routing protocols play in designing an efficient communication system between network nodes. In this context, the lack of adaptive routing mechanisms in the standard Routing Protocol for Low-power and Lossy Networks (RPL), such as load balancing and congestion mechanisms, especially under heavy load scenarios, causes significant degradation of network performance. In this regard, integrating innovative and effective learning abilities, such as Reinforcement Learning, into an efficient routing policy has demonstrated promising solutions for future networks. Hence, this paper introduces Aris-RPL, an adaptive routing policy for the RPL protocol. Aris-RPL utilizes a multi-objective Q-learning algorithm to learn optimal paths. Each node translates neighboring node information into a Q-value representing a composite multi-objective metric, including Buffer Utilization, Energy Level, Received Signal Strength Indicator (RSSI), Overflow Ratio, and Child Count. Furthermore, Aris-RPL operates effectively during the exploitation and exploration phases and continuously monitors the network overflow ratio during exploitation to respond to sudden changes and maintain performance. The extensive Contiki OS 3.0/COOJA simulator experiments have verified Aris-RPL efficiency. It enhanced Control Overhead, Packet Delivery Ratio (PDR), End-to-End Delay (E2E Delay), and Energy Consumption results compared to other counterparts for all scenarios on average by 39%, 25%, 7%, and 38%, respectively. Full article

(This article belongs to the Special Issue Wireless Sensor Networks and Internet of Things)

► Show Figures

Graphical abstract

41 pages, 1830 KB

Open AccessArticle

Cross Layer Optimization Using AI/ML-Assisted Federated Edge Learning in 6G Networks

by Spyridon Louvros, AnupKumar Pandey, Brijesh Shah and Yashesh Buch

Future Internet 2026, 18(2), 71; https://doi.org/10.3390/fi18020071 - 30 Jan 2026

Abstract

This paper introduces a novel methodology that integrates 6G wireless Federated Edge Learning (FEEL) frameworks with MAC to PHY cross layer optimization strategies. In the context of mobile edge computing, typically ensuring robust channel estimation within the 6G network use cases presents critical [...] Read more.

This paper introduces a novel methodology that integrates 6G wireless Federated Edge Learning (FEEL) frameworks with MAC to PHY cross layer optimization strategies. In the context of mobile edge computing, typically ensuring robust channel estimation within the 6G network use cases presents critical challenges, particularly in managing data retransmissions. Inaccurate updates from distributed 6G devices can undermine the reliability of federated learning, affecting its overall performance. To address this, rather than relying on direct evaluations of the objective function, we propose an AI/ML-assisted algorithm for global optimization based on radial basis functions (RBFs) decision-making process to assess learned preference options. Full article

(This article belongs to the Special Issue Toward 6G Networks: Challenges and Technologies)

► Show Figures

Graphical abstract

19 pages, 5729 KB

Open AccessArticle

AI-Driven Hybrid Architecture for Secure, Reconstruction-Resistant Multi-Cloud Storage

by Munir Ahmed and Jiann-Shiun Yuan

Future Internet 2026, 18(2), 70; https://doi.org/10.3390/fi18020070 - 27 Jan 2026

Abstract

Cloud storage continues to experience recurring provider-side breaches, raising concerns about the confidentiality and recoverability of user data. This study addresses this challenge by introducing an Artificial Intelligence (AI)-driven hybrid architecture for secure, reconstruction-resistant multi-cloud storage. The system applies telemetry-guided fragmentation, where fragment [...] Read more.

Cloud storage continues to experience recurring provider-side breaches, raising concerns about the confidentiality and recoverability of user data. This study addresses this challenge by introducing an Artificial Intelligence (AI)-driven hybrid architecture for secure, reconstruction-resistant multi-cloud storage. The system applies telemetry-guided fragmentation, where fragment sizes are dynamically predicted from real-time bandwidth, latency, memory availability and disk I/O, eliminating the predictability of fixed-size fragmentation. All payloads are compressed, encrypted with AES-128 and dispersed across independent cloud providers, while two encrypted fragments are retained within a VeraCrypt-protected local vault to enforce a distributed trust threshold that prevents cloud-only reconstruction. Synthetic telemetry was first used to evaluate model feasibility and scalability, followed by hybrid telemetry integrating real Microsoft system traces and Cisco network metrics to validate generalization under realistic variability. Across all evaluations, XGBoost and Random Forest achieved the highest predictive accuracy, while Neural Network and Linear Regression models provided moderate performance. Security validation confirmed that partial-access and cloud-only attack scenarios cannot yield reconstruction without the local vault fragments and the encryption key. These findings demonstrate that telemetry-driven adaptive fragmentation enhances predictive reliability and establishes a resilient, zero-trust framework for secure multi-cloud storage. Full article

► Show Figures

Graphical abstract

Journal Description

Future Internet

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI