arXiv subjects

Albert Y. Zomaya

Publications and source records attributed to Albert Y. Zomaya.

At least 19 recordsLinked to original sources

arXiv2026

Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems

Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the majority of RL research is conducted in simulation. This reliance introduces challenges related to the Sim-to-Real transferability. Evaluating the Sim-to-Real algorithmic robustness and the Sim-to-Real gap is a critical prerequisite for research aimed at improving RL performance in the real world. Therefore, industries such as robotics have developed concurrent simulation and physical platforms to facilitate this research. However, a universal Sim-to-Real benchmark platform for AIoT does not currently exist. To address these concerns, we developed a real-world AIoT platform for studying RL in AIoT. On this platform, an agent deployed on an edge device plays video games on a separate host computer via a hardware-emulated keyboard, guided by vision input. This platform uses commercially available components costing less than USD 400, together with two computers. Because the system's objective is game score maximization, it inherently mitigates safety risks associated with real-world RL deployments. Experimental results show the simulation-trained agent suffers a 1160% performance degradation relative to the human-level performance after real-world deployment, indicating a significant Sim-to-Real gap. Direct real-world training using the deep Q-network (DQN) algorithm achieves approximately 49% of human-level performance after 10 million training steps, demonstrating the feasibility of RL under real-world conditions. These results suggest that the proposed Sim-to-Real benchmark platform provides a substantial foundation for qualitative and quantitative evaluations of RL in real-world AIoT systems.

cs.AI↗

arXiv2026

Human-Centric Intelligence in the Era of Foundation Models: A Survey

Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated with foundation models to achieve the comparable progress seen in them. More importantly, recent advances across this broad landscape remain fragmented across tasks, modalities, and research communities, leaving their intrinsic conceptual and methodological connections unclear. To bridge these divides and rethink human-centric intelligence in the foundation-model era, we introduce a full-spectrum human context taxonomy that integrates six interconnected levels by viewing humans as observable subjects through visual appearance and spatial geometry, as dynamic actors through kinematic dynamics and interaction modeling, and as situated agents through world simulation and embodied agency. We next present the methodological foundations of the field, covering human-centric data families, computational architecture paradigms, and representative training and inference optimization strategies. We then systematically review representative methods across these levels and organize the associated datasets, benchmarks, and evaluation metrics. We further discuss open challenges and promising research directions toward human-centric intelligence that is scalable, trustworthy, physically grounded, and deployable, aiming to provide a coherent framework and practical reference for advancing the field. Finally, we provide a systematically organized and continuously updated collection of human-centric AI literature and resources on our project page.

cs.CV↗

arXiv2026

ElastiCo: Elastic Configuration and Interference-Aware Orchestration for GPU Clusters

Modern GPU clusters must simultaneously serve deep learning training and offline large language model inference workloads, yet existing schedulers treat these as isolated resource consumers with rigid, static allocations. This leaves substantial GPU capacity underutilized: training jobs reserve entire devices despite periodic idle phases, while offline inference tasks over-provision GPUs despite bursty demand patterns. We present ElastiCo, an elastic co-location framework that enables training and inference workloads to safely share GPUs through three integrated mechanisms. First, Resource Shape Transformation exposes each job as a family of feasible resource-performance configurations. Second, Elastic Shadow Pricing decomposes the resulting multi-resource allocation problem into per-job configuration selection subproblems via dynamic per-resource shadow prices. Third, Interference-Aware Co-location uses a predictor trained on hardware-counter and task-level features to estimate pairwise performance degradation under GPU sharing. Implemented as native Kubernetes middleware requiring no user-code modifications, ElastiCo is evaluated on a 64-GPU testbed and through large-scale trace-driven simulations (up to 512 GPUs), reducing the average JCT by up to 2.94x, increasing the cluster throughput by 2.02x, and increasing the GPU utilization from approximately 25% to 46%.

cs.DC↗

arXiv2026

SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving

As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces a fundamental tension between resource utilization and interactive tail latency. Persistent long-lived sandbox reservations incur excessive memory overhead at scale, while lazy on-demand instantiation generates severe cold-start penalties that degrade response performance under multi-tenant, multi-turn agent workloads. To resolve this dilemma, we present SpecBox, a runtime built around speculative sandbox preallocation tailored for dynamic LLM agent execution pipelines. At its core, SpecBox implements keyword matching and streaming semantic embedding to enable intent-driven sandbox prewarming, which identifies pending tool execution demands mid-LLM token generation and fully overlaps sandbox bootstrapping with model inference. To extend prewarming windows across sequential agent steps, the framework leverages context-aware stochastic prefetching atop a sandbox dependency graph to probabilistically forecast future sandbox switches ahead of execution. We complement these speculative mechanisms with two orthogonal optimizations: a semantic result cache that prunes redundant repeated sandbox invocations, and a dedicated out-of-band shared-memory transport plane that bypasses conventional network serialization to deliver zero-copy artifact transfers. Evaluated on high-concurrency multi-turn agent traces, our prototype demonstrates that SpecBox cuts P99 end-to-end latency by up to $2.9\times$ relative to the on-demand sandbox baseline, while slashing peak memory consumption by $45.9\%$ compared to permanently reserved sandbox deployments.

cs.DC↗

arXiv2026

Agentic Services Computing

Services computing has evolved from Web services and microservices to cloud-native and serverless paradigms. These approaches established mature principles for describing, composing, deploying, operating, and governing reusable software functions. LLM-based agents now introduce a fundamentally different service form. Service value in this paradigm emerges not only from invoking predefined functions but also from delegating goals to autonomous entities. These entities understand context, use tools, collaborate with peers, and act across open environments. This shift raises a core question for services computing. How can goal-driven, stateful, tool-mediated, and accountable autonomous behavior be engineered and managed as a service? Recent studies on LLM agents and multi-agent systems provide important foundations. A clear service-centered research roadmap for this emerging paradigm nevertheless remains absent. This work introduces Agentic Services Computing (ASC) to address this gap. ASC extends services computing from managing reusable functional endpoints to engineering and governing autonomous service entities. It defines agentic services as service-oriented autonomous agents. Related research is organized through a lifecycle view that connects service objects, system structures, enabling infrastructure, evaluation metrics, application evidence, and open challenges. This service-centered perspective establishes a foundation for future service ecosystems. Autonomous agents can thus be systematically described, composed, delivered, monitored, audited, and evolved as first-class services.

cs.SE↗

arXiv2026

HiRL: Hierarchical Reinforcement Learning for Coordinated Resource Management in Heterogeneous Edge Computing

Edge computing faces unprecedented resource orchestration challenges from multi-dimensional heterogeneity across device architectures, diverse task requirements in CPU-intensive, GPU-intensive, I/O-intensive, and dynamic network conditions. The edge environments demand real-time task processing within strict energy budgets, yet conventional approaches struggle with mixed continuous-discrete optimization while meeting deadline and energy constraints. This paper presents HiRL, a hierarchical reinforcement learning framework that decomposes complex resource orchestration into coordinated power control and task allocation decisions. Our approach separates continuous power management using the Twin Delayed Deep Deterministic Policy Gradient (TD3) and discrete task placement using Double Deep Q-Network (DDQN), unified through a coordination engine with five-dimensional queue state representation. We propose a heterogeneous assessment of resource compatibility with deadline-oriented prioritization and failure-penalized adaptive sampling to enhance decision quality under resource constraints. To improve practical applicability, the framework models comprehensive system dynamics including device mobility, queue congestion patterns, infrastructure heterogeneity, and priority-sensitive scheduling demands. Experimental results show that HiRL achieves effective latency-energy trade-offs with 28% latency reduction compared to Single-DDQN and maintains nearly 100% task completion rates under all load conditions. Compared to baseline algorithms, HiRL reduces energy consumption by up to 51% under low load while achieving 24% better latency performance than static optimization approaches under high load, establishing effective resource orchestration in heterogeneous edge environments.

cs.DC↗

arXiv2026

Reliable Microservice Tail Latency Prediction via Decoupled Dual-Stream Learning and Gradient Modulation

Microservice architectures enable scalable cloud-native applications; however, the distributed nature of these systems complicates the maintenance of strict Service Level Objectives. Accurately predicting window-level P95 tail latency remains difficult due to the complex interactions between software workload propagation and infrastructure resource limits. Existing predictive models struggle to capture these dynamics because the lack of explicit separation between traffic metrics and resource metrics causes misaligned feature representations. Building on this suboptimal data treatment, the unified architectures of prior approaches fail to isolate cascading service dependencies from localized processing capacity. Due to this entanglement, joint training suffers from an optimization imbalance wherein resource features converge faster and dominate gradient updates, thereby preventing the learning of underlying software topologies. To address these challenges, we propose USRFNet, a dual-stream framework that separates the modeling of demand and capacity. The proposed framework utilizes a Graph Neural Network to model the spatial interactions of traffic workloads across software-level service dependencies, and a gating MLP to independently extract infrastructure-level resource dynamics. The model then integrates these representations through hierarchical tensor fusion. To resolve the training imbalance, we introduce a Reliability-Aware Gradient Modulation strategy that dynamically rescales gradients based on the generalization ratio of each data stream. Experiments on three large-scale real-world benchmarks demonstrate that USRFNet outperforms state-of-the-art methods in prediction accuracy. Specifically, compared to the best-performing baselines, the proposed framework achieves relative MAPE reductions ranging from 15.62% to 26.11% across the evaluated datasets.

cs.LG↗

arXiv2026

The Evolution of Decentralized Systems: From Gray's Framework to Blockchain and Beyond

Blockchain technology is often discussed as if it emerged from nowhere, yet its architectural DNA traces directly to the decentralized computing principles James~N. Gray articulated in 1986. This paper maps the conceptual lineage from Gray's requestor/server model to modern blockchain architectures, showing how his emphasis on modularity, autonomy, data integrity, and standardized communication anticipated the design of systems like Bitcoin and Ethereum, and, more recently, the Web3 movement and Layer-2 scaling architectures. We examine consensus mechanisms, cryptographic foundations, rollup-based Layer-2 protocols, and cross-chain interoperability through this historical lens, identify persistent challenges in scalability and modularity, and outline future directions toward Web4: an intelligent, decentralized internet integrating blockchain, artificial intelligence, and the Internet of Things.

cs.DC↗

arXiv2025

Edge Intelligence with Spiking Neural Networks

The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational resources and centralized data management, the resulting latency, bandwidth consumption, and privacy concerns have exposed critical limitations in cloud-centric paradigms. Brain-inspired computing, particularly Spiking Neural Networks (SNNs), offers a promising alternative by emulating biological neuronal dynamics to achieve low-power, event-driven computation. This survey provides a comprehensive overview of Edge Intelligence based on SNNs (EdgeSNNs), examining their potential to address the challenges of on-device learning, inference, and security in edge scenarios. We present a systematic taxonomy of EdgeSNN foundations, encompassing neuron models, learning algorithms, and supporting hardware platforms. Three representative practical considerations of EdgeSNN are discussed in depth: on-device inference using lightweight SNN models, resource-aware training and updating under non-stationary data conditions, and secure and privacy-preserving issues. Furthermore, we highlight the limitations of evaluating EdgeSNNs on conventional hardware and introduce a dual-track benchmarking strategy to support fair comparisons and hardware-aware optimization. Through this study, we aim to bridge the gap between brain-inspired learning and practical edge deployment, offering insights into current advancements, open challenges, and future research directions. To the best of our knowledge, this is the first dedicated and comprehensive survey on EdgeSNNs, providing an essential reference for researchers and practitioners working at the intersection of neuromorphic computing and edge intelligence.

cs.DC↗

arXiv2025

Falcon: Advancing Asynchronous BFT Consensus for Lower Latency and Enhanced Throughput

Asynchronous Byzantine Fault Tolerant (BFT) consensus protocols have garnered significant attention with the rise of blockchain technology. A typical asynchronous protocol is designed by executing sequential instances of the Asynchronous Common Sub-seQuence (ACSQ). The ACSQ protocol consists of two primary components: the Asynchronous Common Subset (ACS) protocol and a block sorting mechanism, with the ACS protocol comprising two stages: broadcast and agreement. However, current protocols encounter three critical issues: high latency arising from the execution of the agreement stage, latency instability due to the integral-sorting mechanism, and reduced throughput caused by block discarding. To address these issues,we propose Falcon, an asynchronous BFT protocol that achieves low latency and enhanced throughput. Falcon introduces a novel broadcast protocol, Graded Broadcast (GBC), which enables a block to be included in the ACS set directly, bypassing the agreement stage and thereby reducing latency. To ensure safety, Falcon incorporates a new binary agreement protocol called Asymmetrical Asynchronous Binary Agreement (AABA), designed to complement GBC. Additionally, Falcon employs a partial-sorting mechanism, allowing continuous rather than simultaneous block committing, enhancing latency stability. Finally, we incorporate an agreement trigger that, before its activation, enables nodes to wait for more blocks to be delivered and committed, thereby boosting throughput. We conduct a series of experiments to evaluate Falcon, demonstrating its superior performance.

cs.DC↗

arXiv2025

Personalizing Federated Learning for Hierarchical Edge Networks with Non-IID Data

Accommodating edge networks between IoT devices and the cloud server in Hierarchical Federated Learning (HFL) enhances communication efficiency without compromising data privacy. However, devices connected to the same edge often share geographic or contextual similarities, leading to varying edge-level data heterogeneity with different subsets of labels per edge, on top of device-level heterogeneity. This hierarchical non-Independent and Identically Distributed (non-IID) nature, which implies that each edge has its own optimization goal, has been overlooked in HFL research. Therefore, existing edge-accommodated HFL demonstrates inconsistent performance across edges in various hierarchical non-IID scenarios. To ensure robust performance with diverse edge-level non-IID data, we propose a Personalized Hierarchical Edge-enabled Federated Learning (PHE-FL), which personalizes each edge model to perform well on the unique class distributions specific to each edge. We evaluated PHE-FL across 4 scenarios with varying levels of edge-level non-IIDness, with extreme IoT device level non-IIDness. To accurately assess the effectiveness of our personalization approach, we deployed test sets on each edge server instead of the cloud server, and used both balanced and imbalanced test sets. Extensive experiments show that PHE-FL achieves up to 83 percent higher accuracy compared to existing federated learning approaches that incorporate edge networks, given the same number of training rounds. Moreover, PHE-FL exhibits improved stability, as evidenced by reduced accuracy fluctuations relative to the state-of-the-art FedAvg with two-level (edge and cloud) aggregation.

cs.LG↗

arXiv2024

AutoRank: MCDA Based Rank Personalization for LoRA-Enabled Distributed Learning

As data volumes expand rapidly, distributed machine learning has become essential for addressing the growing computational demands of modern AI systems. However, training models in distributed environments is challenging with participants hold skew, Non-Independent-Identically distributed (Non-IID) data. Low-Rank Adaptation (LoRA) offers a promising solution to this problem by personalizing low-rank updates rather than optimizing the entire model, LoRA-enabled distributed learning minimizes computational and maximize personalization for each participant. Enabling more robust and efficient training in distributed learning settings, especially in large-scale, heterogeneous systems. Despite the strengths of current state-of-the-art methods, they often require manual configuration of the initial rank, which is increasingly impractical as the number of participants grows. This manual tuning is not only time-consuming but also prone to suboptimal configurations. To address this limitation, we propose AutoRank, an adaptive rank-setting algorithm inspired by the bias-variance trade-off. AutoRank leverages the MCDA method TOPSIS to dynamically assign local ranks based on the complexity of each participant's data. By evaluating data distribution and complexity through our proposed data complexity metrics, AutoRank provides fine-grained adjustments to the rank of each participant's local LoRA model. This adaptive approach effectively mitigates the challenges of double-imbalanced, non-IID data. Experimental results demonstrate that AutoRank significantly reduces computational overhead, enhances model performance, and accelerates convergence in highly heterogeneous federated learning environments. Through its strong adaptability, AutoRank offers a scalable and flexible solution for distributed machine learning.

cs.LG↗

arXiv2024

RBLA: Rank-Based-LoRA-Aggregation for Fine-tuning Heterogeneous Models in FLaaS

Federated Learning (FL) is a promising privacy-aware distributed learning framework that can be deployed on various devices, such as mobile phones, desktops, and devices equipped with CPUs or GPUs. In the context of server-based Federated Learning as a Service (FLaaS), FL enables a central server to coordinate the training process across multiple devices without direct access to local data, thereby enhancing privacy and data security. Low-Rank Adaptation (LoRA) is a method that efficiently fine-tunes models by focusing on a low-dimensional subspace of the model's parameters. This approach significantly reduces computational and memory costs compared to fine-tuning all parameters from scratch. When integrated with FL, particularly in a FLaaS environment, LoRA allows for flexible and efficient deployment across diverse hardware with varying computational capabilities by adjusting the local model's rank. However, in LoRA-enabled FL, different clients may train models with varying ranks, which poses challenges for model aggregation on the server. Current methods for aggregating models of different ranks involve padding weights to a uniform shape, which can degrade the global model's performance. To address this issue, we propose Rank-Based LoRA Aggregation (RBLA), a novel model aggregation method designed for heterogeneous LoRA structures. RBLA preserves key features across models with different ranks. This paper analyzes the issues with current padding methods used to reshape models for aggregation in a FLaaS environment. Then, we introduce RBLA, a rank-based aggregation method that maintains both low-rank and high-rank features. Finally, we demonstrate the effectiveness of RBLA through comparative experiments with state-of-the-art methods.

cs.LG↗

arXiv2024

SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks

Federated Learning (FL) is a distributed machine learning paradigm designed for privacy-sensitive applications that run on resource-constrained devices with non-Identically and Independently Distributed (IID) data. Traditional FL frameworks adopt the client-server model with a single-level aggregation (AGR) process, where the server builds the global model by aggregating all trained local models received from client devices. However, this conventional approach encounters challenges, including susceptibility to model/data poisoning attacks. In recent years, advancements in the Internet of Things (IoT) and edge computing have enabled the development of hierarchical FL systems with a two-level AGR process running at edge and cloud servers. In this paper, we propose a Secure Hierarchical FL (SHFL) framework to address poisoning attacks in hierarchical edge networks. By aggregating trained models at the edge, SHFL employs two novel methods to address model/data poisoning attacks in the presence of client adversaries: 1) a client selection algorithm running at the edge for choosing IoT devices to participate in training, and 2) a model AGR method designed based on convex optimization theory to reduce the impact of edge models from networks with adversaries in the process of computing the global model (at the cloud level). The evaluation results reveal that compared to state-of-the-art methods, SHFL significantly increases the maximum accuracy achieved by the global model in the presence of client adversaries applying model/data poisoning attacks.

cs.LG↗

arXiv2024

ACCESS-FL: Agile Communication and Computation for Efficient Secure Aggregation in Stable Federated Learning Networks

Federated Learning (FL) is a promising distributed learning framework designed for privacy-aware applications. FL trains models on client devices without sharing the client's data and generates a global model on a server by aggregating model updates. Traditional FL approaches risk exposing sensitive client data when plain model updates are transmitted to the server, making them vulnerable to security threats such as model inversion attacks where the server can infer the client's original training data from monitoring the changes of the trained model in different rounds. Google's Secure Aggregation (SecAgg) protocol addresses this threat by employing a double-masking technique, secret sharing, and cryptography computations in honest-but-curious and adversarial scenarios with client dropouts. However, in scenarios without the presence of an active adversary, the computational and communication cost of SecAgg significantly increases by growing the number of clients. To address this issue, in this paper, we propose ACCESS-FL, a communication-and-computation-efficient secure aggregation method designed for honest-but-curious scenarios in stable FL networks with a limited rate of client dropout. ACCESS-FL reduces the computation/communication cost to a constant level (independent of the network size) by generating shared secrets between only two clients and eliminating the need for double masking, secret sharing, and cryptography computations. To evaluate the performance of ACCESS-FL, we conduct experiments using the MNIST, FMNIST, and CIFAR datasets to verify the performance of our proposed method. The evaluation results demonstrate that our proposed method significantly reduces computation and communication overhead compared to state-of-the-art methods, SecAgg and SecAgg+.

cs.CR↗

arXiv2024

Analysis of DNS Dependencies and their Security Implications in Australia: A Comparative Study of General and Indigenous Populations

This paper investigates the impact of internet centralization on DNS provisioning, particularly its effects on vulnerable populations such as the indigenous people of Australia. We analyze the DNS dependencies of Australian government domains that serve indigenous communities compared to those serving the general population. Our study categorizes DNS providers into leading (hyperscaler, US-headquartered companies), non-leading (smaller Australian-headquartered or non-Australian companies), and Australian government-hosted providers. Then, we build dependency graphs to demonstrate the direct dependency between Australian government domains and their DNS providers and the indirect dependency involving further layers of providers. Additionally, we conduct an IP location analysis of DNS providers to map out the geographical distribution of DNS servers, revealing the extent of centralization on DNS services within or outside of Australia. Finally, we introduce an attacker model to categorize potential cyber attackers based on their intentions and resources. By considering attacker models and DNS dependency results, we discuss the security vulnerability of each population group against any group of attackers and analyze whether the current setup of the DNS services of Australian government services contributes to a digital divide.

cs.NI↗

arXiv2024

Boosting Communication Efficiency of Federated Learning's Secure Aggregation

Federated Learning (FL) is a decentralized machine learning approach where client devices train models locally and send them to a server that performs aggregation to generate a global model. FL is vulnerable to model inversion attacks, where the server can infer sensitive client data from trained models. Google's Secure Aggregation (SecAgg) protocol addresses this data privacy issue by masking each client's trained model using shared secrets and individual elements generated locally on the client's device. Although SecAgg effectively preserves privacy, it imposes considerable communication and computation overhead, especially as network size increases. Building upon SecAgg, this poster introduces a Communication-Efficient Secure Aggregation (CESA) protocol that substantially reduces this overhead by using only two shared secrets per client to mask the model. We propose our method for stable networks with low delay variation and limited client dropouts. CESA is independent of the data distribution and network size (for higher than 6 nodes), preventing the honest-but-curious server from accessing unmasked models. Our initial evaluation reveals that CESA significantly reduces the communication cost compared to SecAgg.

cs.CR↗

arXiv2024

CGS-Mask: Making Time Series Predictions Intuitive for All

Artificial intelligence (AI) has immense potential in time series prediction, but most explainable tools have limited capabilities in providing a systematic understanding of important features over time. These tools typically rely on evaluating a single time point, overlook the time ordering of inputs, and neglect the time-sensitive nature of time series applications. These factors make it difficult for users, particularly those without domain knowledge, to comprehend AI model decisions and obtain meaningful explanations. We propose CGS-Mask, a post-hoc and model-agnostic cellular genetic strip mask-based saliency approach to address these challenges. CGS-Mask uses consecutive time steps as a cohesive entity to evaluate the impact of features on the final prediction, providing binary and sustained feature importance scores over time. Our algorithm optimizes the mask population iteratively to obtain the optimal mask in a reasonable time. We evaluated CGS-Mask on synthetic and real-world datasets, and it outperformed state-of-the-art methods in elucidating the importance of features over time. According to our pilot user study via a questionnaire survey, CGS-Mask is the most effective approach in presenting easily understandable time series prediction results, enabling users to comprehend the decision-making process of AI models with ease.

cs.AI↗