Sasu Tarkoma

Pranvera Kortoçi, Yilei Liang, Pengyuan Zhou et al.

Mobile devices and the immense amount and variety of data they generate are key enablers of machine learning (ML)-based applications. Traditional ML techniques have shifted toward new paradigms such as federated (FL) and split learning (SL) to improve the protection of user's data privacy. However, these paradigms often rely on server(s) located in the edge or cloud to train computationally-heavy parts of a ML model to avoid draining the limited resource on client devices, resulting in exposing device data to such third parties. This work proposes an alternative approach to train computationally-heavy ML models in user's devices themselves, where corresponding device data resides. Specifically, we focus on GANs (generative adversarial networks) and leverage their inherent privacy-preserving attribute. We train the discriminative part of a GAN with raw data on user's devices, whereas the generative model is trained remotely (e.g., server) for which there is no need to access sensor true data. Moreover, our approach ensures that the computational load of training the discriminative model is shared among user's devices-proportional to their computation capabilities-by means of SL. We implement our proposed collaborative training scheme of a computationally-heavy GAN model in real resource-constrained devices. The results show that our system preserves data privacy, keeps a short training time, and yields same accuracy of model training in unconstrained devices (e.g., cloud). Our code can be found on https://github.com/YukariSonz/FSL-GAN

Henna Kokkonen, Lauri Lovén, Naser Hossein Motlagh et al.

Future AI applications require performance, reliability and privacy that the existing, cloud-dependant system architectures cannot provide. In this article, we study orchestration in the device-edge-cloud continuum, and focus on edge AI for resource orchestration. We claim that to support the constantly growing requirements of intelligent applications in the device-edge-cloud computing continuum, resource orchestration needs to embrace edge AI and emphasize local autonomy and intelligence. To justify the claim, we provide a general definition for continuum orchestration, and look at how current and emerging orchestration paradigms are suitable for the computing continuum. We describe certain major emerging research themes that may affect future orchestration, and provide an early vision of an orchestration paradigm that embraces those research themes. Finally, we survey current key edge AI methods and look at how they may contribute into fulfilling the vision of future continuum orchestration.

Sasu Tarkoma, Roberto Morabito, Jaakko Sauvola

The evolution towards 6G architecture promises a transformative shift in communication networks, with artificial intelligence (AI) playing a pivotal role. This paper delves deep into the seamless integration of Large Language Models (LLMs) and Generalized Pretrained Transformers (GPT) within 6G systems. Their ability to grasp intent, strategize, and execute intricate commands will be pivotal in redefining network functionalities and interactions. Central to this is the AI Interconnect framework, intricately woven to facilitate AI-centric operations within the network. Building on the continuously evolving current state-of-the-art, we present a new architectural perspective for the upcoming generation of mobile networks. Here, LLMs and GPTs will collaboratively take center stage alongside traditional pre-generative AI and machine learning (ML) algorithms. This union promises a novel confluence of the old and new, melding tried-and-tested methods with transformative AI technologies. Along with providing a conceptual overview of this evolution, we delve into the nuances of practical applications arising from such an integration. Through this paper, we envisage a symbiotic integration where AI becomes the cornerstone of the next-generation communication paradigm, offering insights into the structural and functional facets of an AI-native 6G network.

Akrit Mudvari, Antero Vainio, Iason Ofeidis et al.

The growing number of AI-driven applications in mobile devices has led to solutions that integrate deep learning models with the available edge-cloud resources. Due to multiple benefits such as reduction in on-device energy consumption, improved latency, improved network usage, and certain privacy improvements, split learning, where deep learning models are split away from the mobile device and computed in a distributed manner, has become an extensively explored topic. Incorporating compression-aware methods (where learning adapts to compression level of the communicated data) has made split learning even more advantageous. This method could even offer a viable alternative to traditional methods, such as federated learning techniques. In this work, we develop an adaptive compression-aware split learning method ('deprune') to improve and train deep learning models so that they are much more network-efficient, which would make them ideal to deploy in weaker devices with the help of edge-cloud resources. This method is also extended ('prune') to very quickly train deep learning models through a transfer learning approach, which trades off little accuracy for much more network-efficient inference abilities. We show that the 'deprune' method can reduce network usage by 4x when compared with a split-learning approach (that does not use our method) without loss of accuracy, while also improving accuracy over compression-aware split-learning by 4 percent. Lastly, we show that the 'prune' method can reduce the training time for certain models by up to 6x without affecting the accuracy when compared against a compression-aware split-learning approach.

Yanxin Xi, Yu Liu, Tong Li et al.

Cities play an important role in achieving sustainable development goals (SDGs) to promote economic growth and meet social needs. Especially satellite imagery is a potential data source for studying sustainable urban development. However, a comprehensive dataset in the United States (U.S.) covering multiple cities, multiple years, multiple scales, and multiple indicators for SDG monitoring is lacking. To support the research on SDGs in U.S. cities, we develop a satellite imagery dataset using deep learning models for five SDGs containing 25 sustainable development indicators. The proposed dataset covers the 100 most populated U.S. cities and corresponding Census Block Groups from 2014 to 2023. Specifically, we collect satellite imagery and identify objects with state-of-the-art object detection and semantic segmentation models to observe cities' bird's-eye view. We further gather population, nighttime light, survey, and built environment data to depict SDGs regarding poverty, health, education, inequality, and living environment. We anticipate the dataset to help urban policymakers and researchers to advance SDGs-related studies, especially applying satellite imagery to monitor long-term and multi-scale SDGs in cities.

Alaa Saleh, Praveen Kumar Donta, Roberto Morabito et al.

Human biological systems sustain life through extraordinary resilience, continually detecting damage, orchestrating targeted responses, and restoring function through self-healing. Inspired by these capabilities, this paper introduces ReCiSt, a bio-inspired agentic self-healing framework designed to achieve resilience in Distributed Computing Continuum Systems (DCCS). Modern DCCS integrate heterogeneous computing resources, ranging from resource-constrained IoT devices to high-performance cloud infrastructures, and their inherent complexity, mobility, and dynamic operating conditions expose them to frequent faults that disrupt service continuity. These challenges underscore the need for scalable, adaptive, and self-regulated resilience strategies. ReCiSt reconstructs the biological phases of Hemostasis, Inflammation, Proliferation, and Remodeling into the computational layers Containment, Diagnosis, Meta-Cognitive, and Knowledge for DCCS. These four layers perform autonomous fault isolation, causal diagnosis, adaptive recovery, and long-term knowledge consolidation through Language Model (LM)-powered agents. These agents interpret heterogeneous logs, infer root causes, refine reasoning pathways, and reconfigure resources with minimal human intervention. The proposed ReCiSt framework is evaluated on public fault datasets using multiple LMs, and no baseline comparison is included due to the scarcity of similar approaches. Nevertheless, our results, evaluated under different LMs, confirm ReCiSt's self-healing capabilities within tens of seconds with minimum of 10% of agent CPU usage. Our results also demonstrated depth of analysis to over come uncertainties and amount of micro-agents invoked to achieve resilience.

Praveen Kumar Donta, Alaa Saleh, Ying Li et al.

Agentic Artificial Intelligence (AI) represents a fundamental shift in the design of intelligent systems, characterized by interconnected components that collectively enable autonomous perception, reasoning, planning, action, and learning. Recent research on agentic AI has largely focused on technical foundations, including system architectures, reasoning and planning mechanisms, coordination strategies, and application-level performance across domains. However, the societal, ethical, economic, environmental, and governance implications of agentic AI remain weakly integrated into these technical treatments. This paper addresses this gap by presenting a socio-technical analysis of agentic AI that explicitly connects core technical components with societal context. We examine how architectural choices in perception, cognition, planning, execution, and memory introduce dependencies related to data governance, accountability, transparency, safety, and sustainability. To structure this analysis, we adopt the MAD-BAD-SAD construct as an analytical lens, capturing motivations, applications, and moral dilemmas (MAD); biases, accountability, and dangers (BAD); and societal impact, adoption, and design considerations (SAD). Using this lens, we analyze ethical considerations, implications, and challenges arising from contemporary agentic AI systems and assess their manifestation across emerging applications, including healthcare, education, industry, smart and sustainable cities, social services, communications and networking, and earth observation and satellite communications. The paper further identifies open challenges and suggests future research directions, framing agentic AI as an integrated socio-technical system whose behavior and impact are co-produced by algorithms, data, organizational practices, regulatory frameworks, and social norms.

Roberto Morabito, Mallik Tatipamula, Sasu Tarkoma et al.

The network edge's role in Artificial Intelligence (AI) inference processing is rapidly expanding, driven by a plethora of applications seeking computational advantages. These applications strive for data-driven efficiency, leveraging robust AI capabilities and prioritizing real-time responsiveness. However, as demand grows, so does system complexity. The proliferation of AI inference accelerators showcases innovation but also underscores challenges, particularly the varied software and hardware configurations of these devices. This diversity, while advantageous for certain tasks, introduces hurdles in device integration and coordination. In this paper, our objectives are three-fold. Firstly, we outline the requirements and components of a framework that accommodates hardware diversity. Next, we assess the impact of device heterogeneity on AI inference performance, identifying strategies to optimize outcomes without compromising service quality. Lastly, we shed light on the prevailing challenges and opportunities in this domain, offering insights for both the research community and industry stakeholders.

Lauri Lovén, Sujit Gujar, Kalle Timperi et al.

Mechanism-mediated service markets with polymatroidal feasibility admit efficient, dominant-strategy incentive-compatible (DSIC) allocation, but these guarantees implicitly assume truthful execution by the marketplace operator. Modelling the operator as a strategic player, we establish a credibility trilemma: for single-parameter agents on a non-modular polymatroid, no static sealed-bid mechanism is simultaneously revenue-optimal, DSIC for agents, and credible for the operator. We introduce the Cost of Non-Credibility (CoNC) as a price-of-anarchy-style welfare-loss measure and obtain tight $Θ$-bounds across five topology classes (single-edge, series, parallel, tree, series-parallel), plus a matching upper bound $O(|\mathcal{S}|)$ on general DAGs realised by an $Ω(|\mathcal{S}|)$ witness on the SP-augmented sub-family, turning the trilemma into a structural quantity. Three structurally distinct resolutions follow: public broadcast or deferred-revelation commitment, administrative domain separation under settlement separation and four side conditions, and integrator competition orthogonal to mechanism execution under disjoint actors. An instance-level grounding over the edge-pricing market of Amin et al. confirms the trilemma's robustness on a refereed external setting. The result establishes marketplace neutrality as a first-order design constraint on polymatroidal service markets rather than an implementation detail: where the operator is a strategic player, credibility trades off against revenue optimality and agent incentive compatibility along structurally characterised lines.

Lauri Lovén, Roberto Morabito, Abhishek Kumar et al.

The edge-cloud computing continuum demands self-management mechanisms that scale across autonomous administrative domains while honouring tenant- and operator-specified data sovereignty. We present Neural Pub/Sub, a federated-broker autonomic substrate whose self-organising behaviour emerges from market-based price signals rather than centralised control. Its MAPE-K control loop closes over per-broker health and load monitoring, marginal-cost clearing-price analysis, placement planning over a polymatroidal feasibility region, federated cross-domain dispatch, and shared peer subscription summaries with bounded-staleness price signals. The Plan step is anchored in a Walrasian convergence proposition: under gross-substitutes valuations on tree and series-parallel service-dependency DAGs, decentralised price-based allocation matches the welfare of a centralised oracle. We evaluate the substrate on a 4-VM, 4-domain, 48-worker federated edge-cloud testbed (single data centre, 50 ms emulated WAN) in a 1005-run campaign augmented by a fair-process-count sharded-oracle comparator. The federated market dominates a single-process oracle by 2-4% with 45 of 45 per-seed wins (sign-test p ~ 2.8e-14, Hodges-Lehmann median -39.6 ms); against a four-shard centralised orchestrator at equal process count the gap stays within +/-1.5% across all nine (pipeline, load) cells. Round-robin completion rate collapses 98.8% -> 22.4% -> 3.3% across arrival rates 5/10/15 pps while the market preserves completion; the advantage decomposes into three Walrasian properties (information completeness, admission control, price discovery). Federation withstands broker death and network partition (completion rate >= 98.7% across 75 cells), and sovereignty enforcement adds no measurable runtime overhead across 60 governance-grid runs. Heterogeneous-domain stressors and cross-site WAN deployment remain future work.

Lauri Lovén, Abhishek Kumar, Alexander Engelhardt et al.

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and embedding filters. Framed as offline multi-label retrieval over three public datasets spanning social-media, legal, and smart-home sensor domains (six LLMs, seven baselines), our central contribution is a two-crossover cost-accuracy characterisation: an analytical context-window crossover below which a CoverAndMerge compression pipeline reduces LLM invocations, and an empirical discrimination-capacity crossover above which matching accuracy collapses independently of context budget, by a model-dependent factor of parameter count and training generation. Two findings carry practical weight: above the discrimination crossover, compression cannot recover accuracy and only frontier-scale models clear large subscription sets; and there backend choice dominates configuration choice, so model selection, not pipeline tuning, is the primary operator lever. We accompany this with three composable algorithms and a per-cluster Quality-of-Experience framework for autonomic LLM-tier selection.

Mohammad A. Hoque, Matti Siekkinen, Jonghoe Koo et al.

Full charge capacity (FCC) refers to the amount of energy a battery can hold. It is the fundamental property of smartphone batteries that diminishes as the battery ages and is charged/discharged. We investigate the behavior of smartphone batteries while charging and demonstrate that the battery voltage and charging rate information can together characterize the FCC of a battery. We propose a new method for accurately estimating FCC without exposing low-level system details or introducing new hardware or system modules. We also propose and implement a collaborative FCC estimation technique that builds on crowdsourced battery data. The method finds the reference voltage curve and charging rate of a particular smartphone model from the data and then compares the curve and rate of an individual user with the model reference curve. After analyzing a large data set, we report that 55% of all devices and at least one device in 330 out of 357 unique device models lost some of their FCC. For some models, the median capacity loss exceeded 20% with the inter-quartile range being over 20 pp. The models enable debugging the performance of smartphone batteries, more accurate power modeling, and energy-aware system or application optimization.

Roberto Morabito, Bivek Pandey, Paulius Daubaris et al.

Digital Twins (DTs) are set to become a key enabling technology in future wireless networks, with their use in network management increasing significantly. We developed a DT framework that leverages the heterogeneity of network access technologies as a resource for enhanced network performance and management, enabling smart data handling in the physical network. Tested in a Campus Area Network environment, our framework integrates diverse data sources to provide real-time, holistic insights into network performance and environmental sensing. We also envision that traditional analytics will evolve to rely on emerging AI models, such as Generative AI (GenAI), while leveraging current analytics capabilities. This capacity can simplify analytics processes through advanced ML models, enabling descriptive, diagnostic, predictive, and prescriptive analytics in a unified fashion. Finally, we present specific research opportunities concerning interoperability aspects and envision aligning advancements in DT technology with evolved AI integration.

Lauri Lovén, Nam Do, Hassan Mehmood et al.

We prove that no reinforcement learning policy with confidence-gated autonomy can simultaneously achieve maximum helpfulness, optimal calibration, and full autonomy under rational oversight, whenever some tasks exceed the agent's reliable competence: the Behavioral Credibility Trilemma. The impossibility is geometric -- adding any non-affine autonomy incentive to a strictly proper scoring rule destroys strict properness, so an agent rewarded for both calibrated confidence and autonomous action systematically inflates its reported confidence on tasks below the principal's approval threshold. The Behavioral Perturbation Lemma quantifies the inflation (scaling as $w_A/(2 w_C)$ for the Brier score) and shows detection requires $Ω(1/Δ^2)$ observations. We prove the principal's optimal oversight rule is necessarily non-affine, making the impossibility unconditional and optimizer-independent across log-concave-density policy families. We formalize the Confidence-Gated Decision Problem, map existing methods onto the trilemma, and identify two constructive resolution pathways (commitment, domain separation). A 540-configuration Best-of-N experiment tests five pre-registered hypotheses, all strongly confirmed (effect sizes $d = 1.10$ to $5.32$), and adds a descriptive analysis of the achievable-$(H, C, A)$ surface geometry showing a plateau-truncated frontier consistent with the predicted inflation saturation.

Alaa Saleh, Roberto Morabito, Sasu Tarkoma et al.

In today's digital world, Generative Artificial Intelligence (GenAI) such as Large Language Models (LLMs) is becoming increasingly prevalent, extending its reach across diverse applications. This surge in adoption has sparked a significant increase in demand for data-centric GenAI models, highlighting the necessity for robust data communication infrastructures. Central to this need are message brokers, which serve as essential channels for data transfer within various system components. This survey aims to delve into a comprehensive analysis of traditional and modern message brokers, offering a comparative study of prevalent platforms. Our study considers numerous criteria including, but not limited to, open-source availability, integrated monitoring tools, message prioritization mechanisms, capabilities for parallel processing, reliability, distribution and clustering functionalities, authentication processes, data persistence strategies, fault tolerance, and scalability. Furthermore, we explore the intrinsic constraints that the design and operation of each message broker might impose, recognizing that these limitations are crucial in understanding their real-world applicability. Finally, this study examines the enhancement of message broker mechanisms specifically for GenAI contexts, emphasizing the criticality of developing a versatile message broker framework. Such a framework would be poised for quick adaptation, catering to the dynamic and growing demands of GenAI in the foreseeable future. Through this dual-pronged approach, we intend to contribute a foundational compendium that can guide future innovations and infrastructural advancements in the realm of GenAI data communication.

Lauri Lovén, Sasu Tarkoma

Eliciting truthful reports from autonomous agents is a core problem in scalable AI oversight: a principal scores the agent's report using a strictly proper scoring rule, but the agent also benefits from the report through a non-accuracy channel (approval for autonomous action, allocation share, downstream control). The same structure appears in classical mechanism-design settings such as marketplace operation. Our main result is an endogeneity: the principal's optimal oversight necessarily uses a non-affine approval function to screen types, yet any non-affine approval makes truthful reporting suboptimal under the combined objective whenever deviation is undetectable. The principal cannot avoid the perturbation that undermines calibration. This impossibility holds for all strictly proper scoring rules, with a closed-form perturbation formula. A constructive escape exists: a step-function approval threshold achieves first-best screening for every strictly proper scoring rule, because the agent's binary inflate-or-not choice creates a type-space threshold regardless of the generator's curvature. Under the Brier score specifically, the type-independent inflation cost yields a welfare equivalence between second-best and first-best; we prove this equivalence is unique to Brier (the welfare gap under smooth $C^1$ oversight is bounded below by $Ω(\text{Var}(1/G'') (γ/β)^2)$ for every non-Brier rule). Two instances develop the framework: AI agent oversight (the lead motivating setting) and marketplace operation (a parallel mechanism-design domain). The message for AI alignment is direct: smooth scoring-based oversight cannot elicit truthful reports from a strategic agent; sharp thresholds are the calibration-preserving design.

Suvi De Silva, Alfreds Lapkovskis, Alaa Saleh et al.

Grey failures in the computing continuum produce ambiguous overlapping symptoms that existing approaches fail to diagnose reliably, either due to a lack of causal awareness or acting under high epistemic uncertainty, risking destructive interventions. This paper presents an uncertainty-aware resilience micro-agent for causal observability (AURORA), a lightweight framework for diagnosing and mitigating grey failures in edge-tier environments. The framework employs parallel micro-agents that integrate the free-energy principle, causal do-calculus, and localized causal state-graphs to support counterfactual root-cause analysis within each fault's Markov blanket. Restricting inference to causally relevant variables reduces computational overhead while preserving diagnostic fidelity. AURORA further introduces a dual-gated execution mechanism that authorizes remediation only when causal confidence is high and predicted epistemic uncertainty is bounded; otherwise, it abstains from local intervention and escalates the diagnostic payload to the fog tier. Our experiments demonstrate that AURORA outperforms baselines, achieving a 0% destructive action rate, while maintaining 62.0% repair accuracy and a 3ms mean time to repair.

Yanxin Xi, Yu Liu, Zhicheng Liu et al.

The Sustainable Development Goals (SDGs) aim to resolve societal challenges, such as eradicating poverty and improving the lives of vulnerable populations in impoverished areas. Those areas rely on road infrastructure construction to promote accessibility and economic development. Although publicly available data like OpenStreetMap is available to monitor road status, data completeness in impoverished areas is limited. Meanwhile, the development of deep learning techniques and satellite imagery shows excellent potential for earth monitoring. To tackle the challenge of road network assessment in impoverished areas, we develop a systematic road extraction framework combining an encoder-decoder architecture and morphological operations on satellite imagery, offering an integrated workflow for interdisciplinary researchers. Extensive experiments of road network extraction on real-world data in impoverished regions achieve a 42.7% enhancement in the F1-score over the baseline methods and reconstruct about 80% of the actual roads. We also propose a comprehensive road network dataset covering approximately 794,178 km2 area and 17.048 million people in 382 impoverished counties in China. The generated dataset is further utilized to conduct socioeconomic analysis in impoverished counties, showing that road network construction positively impacts regional economic development. The technical appendix, code, and generated dataset can be found at https://github.com/tsinghua-fib-lab/Road_network_extraction_impoverished_counties.

Taufiq Ahmed, Abhishek Kumar, Constantino Álvarez Casado et al.

Object detection models often struggle with class imbalance, where rare categories appear significantly less frequently than common ones. Existing sampling-based rebalancing strategies, such as Repeat Factor Sampling (RFS) and Instance-Aware Repeat Factor Sampling (IRFS), mitigate this issue by adjusting sample frequencies based on image and instance counts. However, these methods are based on linear adjustments, which limit their effectiveness in long-tailed distributions. This work introduces Exponentially Weighted Instance-Aware Repeat Factor Sampling (E-IRFS), an extension of IRFS that applies exponential scaling to better differentiate between rare and frequent classes. E-IRFS adjusts sampling probabilities using an exponential function applied to the geometric mean of image and instance frequencies, ensuring a more adaptive rebalancing strategy. We evaluate E-IRFS on a dataset derived from the Fireman-UAV-RGBT Dataset and four additional public datasets, using YOLOv11 object detection models to identify fire, smoke, people and lakes in emergency scenarios. The results show that E-IRFS improves detection performance by 22\% over the baseline and outperforms RFS and IRFS, particularly for rare categories. The analysis also highlights that E-IRFS has a stronger effect on lightweight models with limited capacity, as these models rely more on data sampling strategies to address class imbalance. The findings demonstrate that E-IRFS improves rare object detection in resource-constrained environments, making it a suitable solution for real-time applications such as UAV-based emergency monitoring. The code is available at: https://github.com/futurians/E-IRFS.

Pengyuan Zhou, Lin Wang, Zhi Liu et al.

This paper offers an insightful examination of how currently top-trending AI technologies, i.e., generative artificial intelligence (Generative AI) and large language models (LLMs), are reshaping the field of video technology, including video generation, understanding, and streaming. It highlights the innovative use of these technologies in producing highly realistic videos, a significant leap in bridging the gap between real-world dynamics and digital creation. The study also delves into the advanced capabilities of LLMs in video understanding, demonstrating their effectiveness in extracting meaningful information from visual content, thereby enhancing our interaction with videos. In the realm of video streaming, the paper discusses how LLMs contribute to more efficient and user-centric streaming experiences, adapting content delivery to individual viewer preferences. This comprehensive review navigates through the current achievements, ongoing challenges, and future possibilities of applying Generative AI and LLMs to video-related tasks, underscoring the immense potential these technologies hold for advancing the field of video technology related to multimedia, networking, and AI communities.

Talha Zeeshan, Abhishek Kumar, Susanna Pirttikangas et al.

This paper presents the development and evaluation of a Large Language Model (LLM), also known as foundation models, based multi-agent system framework for complex event processing (CEP) with a focus on video query processing use cases. The primary goal is to create a proof-of-concept (POC) that integrates state-of-the-art LLM orchestration frameworks with publish/subscribe (pub/sub) tools to address the integration of LLMs with current CEP systems. Utilizing the Autogen framework in conjunction with Kafka message brokers, the system demonstrates an autonomous CEP pipeline capable of handling complex workflows. Extensive experiments evaluate the system's performance across varying configurations, complexities, and video resolutions, revealing the trade-offs between functionality and latency. The results show that while higher agent count and video complexities increase latency, the system maintains high consistency in narrative coherence. This research builds upon and contributes to, existing novel approaches to distributed AI systems, offering detailed insights into integrating such systems into existing infrastructures.

Aygün Varol, Naser Hossein Motlagh, Mirka Leino et al.

Smart spaces are ubiquitous computing environments that integrate diverse sensing and communication technologies to enhance space functionality, optimize energy utilization, and improve user comfort and well-being. The integration of emerging AI methodologies into these environments facilitates the formation of AI-driven smart spaces, which further enhance functionalities of the spaces by enabling advanced applications such as personalized comfort settings, interactive living spaces, and automatization of the space systems, all resulting in enhanced indoor experiences of the users. In this paper, we present a systematic survey of existing research on the foundational components of AI-driven smart spaces, including sensor technologies, data communication protocols, sensor network management and maintenance strategies, as well as the data collection, processing and analytics. Given the pivotal role of AI in establishing AI-powered smart spaces, we explore the opportunities and challenges associated with traditional machine learning (ML) approaches, such as deep learning (DL), and emerging methodologies including large language models (LLMs). Finally, we provide key insights necessary for the development of AI-driven smart spaces, propose future research directions, and sheds light on the path forward.

Guanghan Wu, Sasu Tarkoma, Roberto Morabito

The evolving requirements of Internet of Things (IoT) applications are driving an increasing shift toward bringing intelligence to the edge, enabling real-time insights and decision-making within resource-constrained environments. Tiny Machine Learning (TinyML) has emerged as a key enabler of this evolution, facilitating the deployment of ML models on devices such as microcontrollers and embedded systems. However, the complexity of managing the TinyML lifecycle, including stages such as data processing, model optimization and conversion, and device deployment, presents significant challenges and often requires substantial human intervention. Motivated by these challenges, we began exploring whether Large Language Models (LLMs) could help automate and streamline the TinyML lifecycle. We developed a framework that leverages the natural language processing (NLP) and code generation capabilities of LLMs to reduce development time and lower the barriers to entry for TinyML deployment. Through a case study involving a computer vision classification model, we demonstrate the framework's ability to automate key stages of the TinyML lifecycle. Our findings suggest that LLM-powered automation holds potential for improving the lifecycle development process and adapting to diverse requirements. However, while this approach shows promise, there remain obstacles and limitations, particularly in achieving fully automated solutions. This paper sheds light on both the challenges and opportunities of integrating LLMs into TinyML workflows, providing insights into the path forward for efficient, AI-assisted embedded system development.

Alaa Saleh, Sasu Tarkoma, Praveen Kumar Donta et al.

Agentic AI, with its autonomous and proactive decision-making, has transformed smart environments. By integrating Generative AI (GenAI) and multi-agent systems, modern AI frameworks can dynamically adapt to user preferences, optimize data management, and improve resource allocation. This paper introduces UserCentrix, an agentic memory-augmented AI framework designed to enhance smart spaces through dynamic, context-aware decision-making. This framework integrates personalized Large Language Model (LLM) agents that leverage user preferences and LLM memory management to deliver proactive and adaptive assistance. Furthermore, it incorporates a hybrid hierarchical control system, balancing centralized and distributed processing to optimize real-time responsiveness while maintaining global situational awareness. UserCentrix achieves resource-efficient AI interactions by embedding memory-augmented reasoning, cooperative agent negotiation, and adaptive orchestration strategies. Our key contributions include (i) a self-organizing framework with proactive scaling based on task urgency, (ii) a Value of Information (VoI)-driven decision-making process, (iii) a meta-reasoning personal LLM agent, and (iv) an intelligent multi-agent coordination system for seamless environment adaptation. Experimental results across various models confirm the effectiveness of our approach in enhancing response accuracy, system efficiency, and computational resource management in real-world application.

Maximilian Abstreiter, Sasu Tarkoma, Roberto Morabito

The rapid rise of Language Models (LMs) has expanded the capabilities of natural language processing, powering applications from text generation to complex decision-making. While state-of-the-art LMs often boast hundreds of billions of parameters and are primarily deployed in data centers, recent trends show a growing focus on compact models-typically under 10 billion parameters-enabled by techniques such as quantization and other model compression techniques. This shift paves the way for LMs on edge devices, offering potential benefits such as enhanced privacy, reduced latency, and improved data sovereignty. However, the inherent complexity of even these smaller models, combined with the limited computing resources of edge hardware, raises critical questions about the practical trade-offs in executing LM inference outside the cloud. To address these challenges, we present a comprehensive evaluation of generative LM inference on representative CPU-based and GPU-accelerated edge devices. Our study measures key performance indicators-including memory usage, inference speed, and energy consumption-across various device configurations. Additionally, we examine throughput-energy trade-offs, cost considerations, and usability, alongside an assessment of qualitative model performance. While quantization helps mitigate memory overhead, it does not fully eliminate resource bottlenecks, especially for larger models. Our findings quantify the memory and energy constraints that must be considered for practical real-world deployments, offering concrete insights into the trade-offs between model size, inference performance, and efficiency. The exploration of LMs at the edge is still in its early stages. We hope this study provides a foundation for future research, guiding the refinement of models, the enhancement of inference efficiency, and the advancement of edge-centric AI systems.

Alaa Saleh, Roberto Morabito, Sasu Tarkoma et al.

As 6G networks evolve into increasingly AI-driven, user-centric ecosystems, traditional reactive handover mechanisms demonstrate limitations, especially in mobile edge computing and autonomous agent-based service scenarios. This manuscript introduces WAAN, a cross-layer framework that enables intent-aware and proactive handovers by embedding lightweight TinyML agents as autonomous, negotiation-capable entities across heterogeneous edge nodes that contribute to intent propagation and network adaptation. To ensure continuity across mobility-induced disruptions, WAAN incorporates semi-stable rendezvous points that serve as coordination anchors for context transfer and state preservation. The framework's operational capabilities are demonstrated through a multimodal environmental control case study, highlighting its effectiveness in maintaining user experience under mobility. Finally, the article discusses key challenges and future opportunities associated with the deployment and evolution of WAAN.

Martha Arbayani Zaidan, Naser Hossein Motlagh, Petteri Nurmi et al.

Atmospheric sciences are crucial for understanding environmental phenomena ranging from air quality to extreme weather events, and climate change. Recent breakthroughs in sensing, communication, computing, and Artificial Intelligence (AI) have significantly advanced atmospheric sciences, enabling the generation of vast amounts of data through long-term Earth observations and providing powerful tools for analyzing atmospheric phenomena and predicting natural disasters. This paper contributes a critical interdisciplinary overview that bridges the fields of atmospheric science and computer science, highlighting the transformative potential of AI in atmospheric research. We identify key challenges associated with integrating AI into atmospheric research, including issues related to big data and infrastructure, and provide a detailed research roadmap that addresses both current and emerging challenges.

Aaron Yi Ding, Ella Peltonen, Tobias Meuser et al.

Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI. In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimization, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The Edge AI community investigates novel ML methods for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The goal is to share an envisioned roadmap that can bring together key actors and enablers to further advance the domain of Edge AI.

Pengyuan Zhou, Pranvera Kortoci, Yui-Pan Yau et al.

Connected vehicles, whether equipped with advanced driver-assistance systems or fully autonomous, require human driver supervision and are currently constrained to visual information in their line-of-sight. A cooperative perception system among vehicles increases their situational awareness by extending their perception range. Existing solutions focus on improving perspective transformation and fast information collection. However, such solutions fail to filter out large amounts of less relevant data and thus impose significant network and computation load. Moreover, presenting all this less relevant data can overwhelm the driver and thus actually hinder them. To address such issues, we present Augmented Informative Cooperative Perception (AICP), the first fast-filtering system which optimizes the informativeness of shared data at vehicles to improve the fused presentation. To this end, an informativeness maximization problem is presented for vehicles to select a subset of data to display to their drivers. Specifically, we propose (i) a dedicated system design with custom data structure and lightweight routing protocol for convenient data encapsulation, fast interpretation and transmission, and (ii) a comprehensive problem formulation and efficient fitness-based sorting algorithm to select the most valuable data to display at the application layer. We implement a proof-of-concept prototype of AICP with a bandwidth-hungry, latency-constrained real-life augmented reality application. The prototype adds only 12.6 milliseconds of latency to a current informativeness-unaware system. Next, we test the networking performance of AICP at scale and show that ACIP effectively filters out less relevant packets and decreases the channel busy time.

Md. Saiful Islam Bhuiyan, Abdur Razzak, Md Sadek Ferdous et al.

A Chatbot is a popular platform to enable users to interact with a software or website to gather information or execute actions in an automated fashion. In recent years, chatbots are being used for executing financial transactions, however, there are a number of security issues, such as secure authentication, data integrity, system availability and transparency, that must be carefully handled for their wide-scale adoption. Recently, the blockchain technology, with a number of security advantages, has emerged as one of the foundational technologies with the potential to disrupt a number of application domains, particularly in the financial sector. In this paper, we forward the idea of integrating a chatbot with blockchain technology in the view to improve the security issues in financial chatbots. More specifically, we present BONIK, a blockchain empowered chatbot for financial transactions, and discuss its architecture and design choices. Furthermore, we explore the developed Proof-of-Concept (PoC), evaluate its performance, analyse how different security and privacy issues are mitigated using BONIK.

Francesco Concas, Jukka K. Nurminen, Tommi Mikkonen et al.

As a part of the digital transformation, we interact with more and more intelligent gadgets. Today, these gadgets are often mobile devices, but in the advent of smart cities, more and more infrastructure---such as traffic and buildings---in our surroundings becomes intelligent. The intelligence, however, does not emerge by itself. Instead, we need both design techniques to create intelligent systems, as well as approaches to validate their correct behavior. An example of intelligent systems that could benefit smart cities are self-driving vehicles. Self-driving vehicles are continuously becoming both commercially available and common on roads. Accidents involving self-driving vehicles, however, have raised concerns about their reliability. Due to these concerns, the safety of self-driving vehicles should be thoroughly tested before they can be released into traffic. To ensure that self-driving vehicles encounter all possible scenarios, several millions of hours of testing must be carried out; therefore, testing self-driving vehicles in the real world is impractical. There is also the issue that testing self-driving vehicles directly in the traffic poses a potential safety hazard to human drivers. To tackle this challenge, validation frameworks for testing self-driving vehicles in simulated scenarios are being developed by academia and industry. In this chapter, we briefly introduce self-driving vehicles and give an overview of validation frameworks for testing them in a simulated environment. We conclude by discussing what an ideal validation framework at the state of the art should be and what could benefit validation frameworks for self-driving vehicles in the future.

Ella Peltonen, Mehdi Bennis, Michele Capobianco et al.

In this white paper we provide a vision for 6G Edge Intelligence. Moving towards 5G and beyond the future 6G networks, intelligent solutions utilizing data-driven machine learning and artificial intelligence become crucial for several real-world applications including but not limited to, more efficient manufacturing, novel personal smart device environments and experiences, urban computing and autonomous traffic settings. We present edge computing along with other 6G enablers as a key component to establish the future 2030 intelligent Internet technologies as shown in this series of 6G White Papers. In this white paper, we focus in the domains of edge computing infrastructure and platforms, data and edge network management, software development for edge, and real-time and distributed training of ML/AI algorithms, along with security, privacy, pricing, and end-user aspects. We discuss the key enablers and challenges and identify the key research questions for the development of the Intelligent Edge services. As a main outcome of this white paper, we envision a transition from Internet of Things to Intelligent Internet of Intelligent Things and provide a roadmap for development of 6G Intelligent Edge.

Dianlei Xu, Tong Li, Yong Li et al.

Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence. The aim of edge intelligence is to enhance the quality and speed of data processing and protect the privacy and security of the data. Although recently emerged, spanning the period from 2011 to now, this field of research has shown explosive growth over the past five years. In this paper, we present a thorough and comprehensive survey on the literature surrounding edge intelligence. We first identify four fundamental components of edge intelligence, namely edge caching, edge training, edge inference, and edge offloading, based on theoretical and practical results pertaining to proposed and deployed systems. We then aim for a systematic classification of the state of the solutions by examining research results and observations for each of the four components and present a taxonomy that includes practical problems, adopted techniques, and application goals. For each category, we elaborate, compare and analyse the literature from the perspectives of adopted techniques, objectives, performance, advantages and drawbacks, etc. This survey article provides a comprehensive introduction to edge intelligence and its application areas. In addition, we summarise the development of the emerging research field and the current state-of-the-art and discuss the important open issues and possible theoretical and technical solutions.

Abhishek Kumar, Benjamin Finley, Tristan Braud et al.

Artificial intelligence shows promise for solving many practical societal problems in areas such as healthcare and transportation. However, the current mechanisms for AI model diffusion such as Github code repositories, academic project webpages, and commercial AI marketplaces have some limitations; for example, a lack of monetization methods, model traceability, and model auditabilty. In this work, we sketch guidelines for a new AI diffusion method based on a decentralized online marketplace. We consider the technical, economic, and regulatory aspects of such a marketplace including a discussion of solutions for problems in these areas. Finally, we include a comparative analysis of several current AI marketplaces that are already available or in development. We find that most of these marketplaces are centralized commercial marketplaces with relatively few models.

Francesco Concas, Julien Mineraud, Eemil Lagerspetz et al.

The significance of air pollution and the problems associated with it are fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which unfortunately are very expensive both to acquire and to maintain. Hence environmental monitoring stations are typically sparsely deployed, resulting in limited spatial resolution for measurements. Recently, low-cost air quality sensors have emerged as an alternative that can improve the granularity of monitoring. The use of low-cost air quality sensors, however, presents several challenges: they suffer from cross-sensitivities between different ambient pollutants; they can be affected by external factors, such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Periodic re-calibration can improve the accuracy of low-cost sensors, particularly with machine-learning-based calibration, which has shown great promise due to its capability to calibrate sensors in-field. In this article, we survey the rapidly growing research landscape of low-cost sensor technologies for air quality monitoring and their calibration using machine learning techniques. We also identify open research challenges and present directions for future research.

Joonas Jälkö, Eemil Lagerspetz, Jari Haukka et al.

Differential privacy allows quantifying privacy loss resulting from accessing sensitive personal data. Repeated accesses to underlying data incur increasing loss. Releasing data as privacy-preserving synthetic data would avoid this limitation, but would leave open the problem of designing what kind of synthetic data. We propose formulating the problem of private data release through probabilistic modelling. This approach transforms the problem of designing the synthetic data into choosing a model for the data, allowing also including prior knowledge, which improves the quality of the synthetic data. We demonstrate empirically, in an epidemiological study, that statistical discoveries can be reliably reproduced from the synthetic data. We expect the method to have broad use in creating high-quality anonymized data twins of key data sets for research.

Ibbad Hafeez, Markku Antikainen, Aaron Yi Ding et al.

The increased popularity of IoT devices have made them lucrative targets for attackers. Due to insecure product development practices, these devices are often vulnerable even to very trivial attacks and can be easily compromised. Due to the sheer number and heterogeneity of IoT devices, it is not possible to secure the IoT ecosystem using traditional endpoint and network security solutions. To address the challenges and requirements of securing IoT devices in edge networks, we present IoT-Keeper, which is a novel system capable of securing the network against any malicious activity, in real time. The proposed system uses a lightweight anomaly detection technique, to secure both device-to-device and device-to-infrastructure communications, while using limited resources available on the gateway. It uses unlabeled network data to distinguish between benign and malicious traffic patterns observed in the network. A detailed evaluation, done with real world testbed, shows that IoT-Keeper detects any device generating malicious traffic with high accuracy (0.982) and low false positive rate (0.01). The results demonstrate that IoT-Keeper is lightweight, responsive and can effectively handle complex D2D interactions without requiring explicit attack signatures or sophisticated hardware.

Hien Thi Thu Truong, Juhani Toivonen, Thien Duc Nguyen et al.

Copresence verification based on context can improve usability and strengthen security of many authentication and access control systems. By sensing and comparing their surroundings, two or more devices can tell whether they are copresent and use this information to make access control decisions. To the best of our knowledge, all context-based copresence verification mechanisms to date are susceptible to context-manipulation attacks. In such attacks, a distributed adversary replicates the same context at the (different) locations of the victim devices, and induces them to believe that they are copresent. In this paper we propose DoubleEcho, a context-based copresence verification technique that leverages acoustic Room Impulse Response (RIR) to mitigate context-manipulation attacks. In DoubleEcho, one device emits a wide-band audible chirp and all participating devices record reflections of the chirp from the surrounding environment. Since RIR is, by its very nature, dependent on the physical surroundings, it constitutes a unique location signature that is hard for an adversary to replicate. We evaluate DoubleEcho by collecting RIR data with various mobile devices and in a range of different locations. We show that DoubleEcho mitigates context-manipulation attacks whereas all other approaches to date are entirely vulnerable to such attacks. DoubleEcho detects copresence (or lack thereof) in roughly 2 seconds and works on commodity devices.

Ibbad Hafeez, Aaron Yi Ding, Sasu Tarkoma

The number of mobile and IoT devices connected to home and enterprise networks is growing fast. These devices offer new services and experiences for the users; however, they also present new classes of security threats pertaining to data and device safety and user privacy. In this article, we first analyze the potential threats presented by these devices connected to edge networks. We then propose Securebox: a new cloud-driven, low cost Security-as-a-Service solution that applies Software-Defined Networking (SDN) to improve network monitoring, security and management. Securebox enables remote management of networks through a cloud security service (CSS) with minimal user intervention required. To reduce costs and improve the scalability, Securebox is based on virtualized middleboxes provided by CSS. Our proposal differs from the existing solutions by integrating the SDN and cloud into a unified edge security solution, and by offering a collaborative protection mechanism that enables rapid security policy dissemination across all connected networks in mitigating new threats or attacks detected by the system. We have implemented two Securebox prototypes, using a low-cost Raspberry-PI and off-the-shelf fanless PC. Our system evaluation has shown that Securebox can achieve automatic network security and be deployed incrementally to the infrastructure with low management overhead.

Ibbad Hafeez, Aaron Yi Ding, Markku Antikainen et al.

The growing popularity of Internet-of-Things (IoT) has created the need for network-based traffic anomaly detection systems that could identify misbehaving devices. In this work, we propose a lightweight technique, IoT-guard, for identifying malicious traffic flows. IoT-guard uses semi-supervised learning to distinguish between malicious and benign device behaviours using the network traffic generated by devices. In order to achieve this, we extracted 39 features from network logs and discard any features containing redundant information. After feature selection, fuzzy C-Mean (FCM) algorithm was trained to obtain clusters discriminating benign traffic from malicious traffic. We studied the feature scores in these clusters and use this information to predict the type of new traffic flows. IoT-guard was evaluated using a real-world testbed with more than 30 devices. The results show that IoTguard achieves high accuracy (98%), in differentiating various types of malicious and benign traffic, with low false positive rates. Furthermore, it has low resource footprint and can operate on OpenWRT enabled access points and COTS computing boards.

Mikko Heikkilä, Eemil Lagerspetz, Samuel Kaski et al.

Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects. Differential privacy (DP) has become established as a standard for protecting learning results. The standard DP algorithms require a single trusted party to have access to the entire data, which is a clear weakness. We consider DP Bayesian learning in a distributed setting, where each party only holds a single sample or a few samples of the data. We propose a learning strategy based on a secure multi-party sum function for aggregating summaries from data holders and the Gaussian mechanism for DP. Our method builds on an asymptotically optimal and practically efficient DP Bayesian inference with rapidly diminishing extra cost.

Markus Miettinen, Samuel Marchal, Ibbad Hafeez et al.

With the rapid growth of the Internet-of-Things (IoT), concerns about the security of IoT devices have become prominent. Several vendors are producing IP-connected devices for home and small office networks that often suffer from flawed security designs and implementations. They also tend to lack mechanisms for firmware updates or patches that can help eliminate security vulnerabilities. Securing networks where the presence of such vulnerable devices is given, requires a brownfield approach: applying necessary protection measures within the network so that potentially vulnerable devices can coexist without endangering the security of other devices in the same network. In this paper, we present IOT SENTINEL, a system capable of automatically identifying the types of devices being connected to an IoT network and enabling enforcement of rules for constraining the communications of vulnerable devices so as to minimize damage resulting from their compromise. We show that IOT SENTINEL is effective in identifying device types and has minimal performance overhead.

Julien Mineraud, Sasu Tarkoma

The Internet of Things (IoT) envisions that objects may be connected to the Internet, producing and consuming data in real-time. Today, numerous middleware platforms are available to facilitate the communication with these objects. Unfortunately, the interoperability of these platforms is very limited because it requires to "manually" connect the services proposed by each platform. One key design goal for our contribution is not to build yet another middleware, but rather to augment the functionalities of existing systems via an extension to support their integration into a network of heterogeneous IoT hubs. The extension includes a RESTful API to manipulate the basic component of our extension, the IoT feeds. The IoT feeds allow the platform's owner to dynamically marshal the IoT features connected to the platform, as well as the data that they produce. Furthermore, the feeds enable the owner to manage and control the data flows before connecting them to his applications. Subsequently, these feeds may also be published to meta-hubs in order to expose them to third parties. We evaluated an implementation our extension for Android systems to show the feasibility of managing the data flows using the RESTful API on this platform.

Mohammad Ashraful Hoque, Matti Siekkinen, Jukka K. Nurminen et al.

This paper proposes a novel energy-efficient multimedia delivery system called EStreamer. First, we study the relationship between buffer size at the client, burst-shaped TCP-based multimedia traffic, and energy consumption of wireless network interfaces in smartphones. Based on the study, we design and implement EStreamer for constant bit rate and rate-adaptive streaming. EStreamer can improve battery lifetime by 3x, 1.5x and 2x while streaming over Wi-Fi, 3G and 4G respectively.

Hien Thi Thu Truong, Eemil Lagerspetz, Petteri Nurmi et al.

There is little information from independent sources in the public domain about mobile malware infection rates. The only previous independent estimate (0.0009%) [12], was based on indirect measurements obtained from domain name resolution traces. In this paper, we present the first independent study of malware infection rates and associated risk factors using data collected directly from over 55,000 Android devices. We find that the malware infection rates in Android devices estimated using two malware datasets (0.28% and 0.26%), though small, are significantly higher than the previous independent estimate. Using our datasets, we investigate how indicators extracted inexpensively from the devices correlate with malware infection. Based on the hypothesis that some application stores have a greater density of malicious applications and that advertising within applications and cross-promotional deals may act as infection vectors, we investigate whether the set of applications used on a device can serve as an indicator for infection of that device. Our analysis indicates that this alone is not an accurate indicator for pinpointing infection. However, it is a very inexpensive but surprisingly useful way for significantly narrowing down the pool of devices on which expensive monitoring and analysis mechanisms must be deployed. Using our two malware datasets we show that this indicator performs 4.8 and 4.6 times (respectively) better at identifying infected devices than the baseline of random checks. Such indicators can be used, for example, in the search for new or previously undetected malware. It is therefore a technique that can complement standard malware scanning by anti-malware tools. Our analysis also demonstrates a marginally significant difference in battery use between infected and clean devices.

Mohammad Ashraful Hoque, Matti Siekkinen, Jukka K. Nurminen et al.

Multimedia streaming to mobile devices is challenging for two reasons. First, the way content is delivered to a client must ensure that the user does not experience a long initial playback delay or a distorted playback in the middle of a streaming session. Second, multimedia streaming applications are among the most energy hungry applications in smartphones. The energy consumption mostly depends on the delivery techniques and on the power management techniques of wireless access technologies (Wi-Fi, 3G, and 4G). In order to provide insights on what kind of streaming techniques exist, how they work on different mobile platforms, their efforts in providing smooth quality of experience, and their impact on energy consumption of mobile phones, we did a large set of active measurements with several smartphones having both Wi-Fi and cellular network access. Our analysis reveals five different techniques to deliver the content to the video players. The selection of a technique depends on the mobile platform, device, player, quality, and service. The results from our traffic and power measurements allow us to conclude that none of the identified techniques is optimal because they take none of the following facts into account: access technology used, user behavior, and user preferences concerning data waste. We point out the technique with optimal playback buffer configuration, which provides the most attractive trade-offs in particular situations.