arXiv subjects

Sai Zou

Publications and source records attributed to Sai Zou.

11 recordsLinked to original sources

arXiv2026

HermesHFL: Incentive-Compatible Hierarchical Federated Unlearning for Dynamic LLM Fine-Tuning

Hierarchical federated unlearning (HFUL) for large language model (LLM) fine-tuning faces significant challenges due to hierarchical aggregation, dynamic client participation, and strong parameter coupling in LLM adaptation. Selectively removing client contributions is particularly difficult because model updates propagate across multiple aggregation stages while unlearning requests may coincide with client departures and rejoining. To address these issues, we propose HermesHFL, a hierarchical federated learning framework that supports selective unlearning, dynamic client participation, and client reintegration for scalable LLM fine-tuning via parameter-efficient fine-tuning (PEFT) with LoRA. We formulate a unified optimization problem that jointly models client participation, edge association, incentive allocation, and unlearning under heterogeneous client behaviors. To solve this problem efficiently, we develop Neogen, a neural-guided bilevel evolutionary optimization framework that combines CMA-ES for continuous incentive optimization with a CHC-based evolutionary mechanism for discrete participation and association decisions. A neural surrogate further accelerates optimization and improves search efficiency. Extensive experiments on LLM fine-tuning tasks demonstrate that HermesHFL consistently outperforms state-of-the-art baselines in model utility, unlearning effectiveness, convergence stability, and resource efficiency.

cs.CE↗

arXiv2026

AEGIS: Risk-Budgeted Online Scheduling for Resilient Continuous Edge Inference

Continuous edge inference requires sustained wireless and computing support across successive service instances. Under recurring channel degradation, transient edge overload, and multi-user contention, isolated deadline misses may accumulate into persistent service degradation. Existing schedulers mainly optimize instantaneous latency or per-timeslot utility and provide limited control over such cross-time effects. To address this issue, we propose AEGIS (Adaptive Exposure-Governed Inference Scheduling), a risk-budgeted online framework for service-level operational resilience. AEGIS regulates predicted deadline-risk exposure through dynamically replenished per-user risk budgets and establishes an explicit finite-horizon bound on cumulative admitted-risk exposure. One-step state estimation supports anticipatory delay and risk assessment, while the centralized bandwidth--computing allocation is transformed into an exact-potential formulation and solved through asynchronous coordinate updates. Simulation results demonstrate that AEGIS enhances timely-service continuity, contains persistent deadline violations, and improves post-stress recovery through adaptive cross-time risk regulation. Meanwhile, it effectively controls predicted-risk exposure while preserving competitive service performance, achieving a favorable balance between service resilience and risk control.

cs.NI↗

arXiv2026

Masking Intent, Sustaining Equilibrium: Risk-Aware Potential-Game-Based Service Provision in Dynamic Mobile Crowdsensing

Mobile crowdsensing (MCS) is evolving from basic data collection to dynamic service provisioning, where platforms must maintain task completion, budget feasibility, and sensing quality under uncertain worker availability. Beyond raw-data and location privacy, workers' long-term intent traces, such as task-selection tendencies and participation histories, can be exploited by an honest-but-curious platform to infer private preferences from one or multiple allocation snapshots. Worker dropouts and execution uncertainty further destabilize sensing coverage, while frequent global re-optimization increases interaction overhead and observable exposure. To address these issues, we propose \textit{iParts}, an intent-preserving and risk-aware two-stage service provisioning framework for dynamic MCS. In the offline stage, workers report perturbed intent vectors through personalized local differential privacy with memoized permanent randomized response, suppressing frequency-based intent inference while retaining decision utility. The platform then builds a redundancy-aware quality model and performs risk-aware pre-planning under budget, quality-risk, and intent-mismatch constraints. This offline problem is formulated as an exact potential game with expected social welfare as the potential function, guaranteeing constrained equilibrium existence and finite-step convergence under feasible improvement dynamics. In the online stage, quality deficits are repaired through bounded-round temporary recruitment from idle or standby workers, enabling feasibility-preserving adjustment with limited exposure. Experiments show that iParts improves welfare and task completion while reducing redundancy and communication overhead against representative benchmarks.

cs.NI↗

arXiv2025

FUSION: Forecast-Embedded Agent Scheduling with Service Incentive Optimization over Distributed Air-Ground Edge Networks

In this paper, we introduce a first-of-its-kind forecasting-driven, incentive-aware service provisioning framework for distributed air-ground integrated networks that explicitly accounts for human-machine coexistence. In our framework, vehicular-UAV agent pairs (APs) are proactively dispatched to overloaded hotspots to augment the computing capacity of edge servers (ESs), which in turn gives rise to a set of challenges that we jointly address: highly uncertain spatio-temporal workloads, spatio-temporal coupling between road traffic and UAV capacity, forecast-driven contracting risks, and heterogeneous quality-of-service (QoS) requirements of human users (HUs) and machine users (MUs). To address these challenges, we propose FUSION, a two-stage optimization framework, consisting of an offline stage and an online stage. In the offline stage, a liquid neural network-powered module performs multi-step spatio-temporal demand forecasting at distributed ESs, whose outputs are exploited by an enhanced ant colony optimization-based routing scheme and an auction-based incentive-aware contracting mechanism, to jointly determine ES-AP contracts and pre-planned service routes. In the online stage, we model congestion-aware task scheduling as a service demander-side exact-potential game, where HUs and MUs select either local execution or accessible ES/UAV resources, and develop a potential-guided best-response dynamics algorithm that converges to an \varepsilon-NE under a positive improvement threshold and to a pure-strategy Nash equilibrium when the threshold is zero. Experiments on both synthetic and real-world datasets show that FUSION consistently achieves higher social welfare and improved resource utilization, while maintaining latency and energy costs comparable to state-of-the-art baselines and preserving individual rationality, budget balance, and near-truthfulness.

cs.NI↗

arXiv2025

Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents

Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and collaborate at scale. Within this paradigm, federated fine-tuning (FFT) serves as a key enabler that allows distributed LLM agents to co-train an intelligent global LLM without centralizing local datasets. However, the FFT-enabled IoA systems remain vulnerable to model poisoning attacks, where adversaries can upload malicious updates to the server to degrade the performance of the aggregated global LLM. This paper proposes a graph representation-based model poisoning (GRMP) attack, which exploits overheard benign updates to construct a feature correlation graph and employs a variational graph autoencoder to capture structural dependencies and generate malicious updates. A novel attack algorithm is developed based on augmented Lagrangian and subgradient descent methods to optimize malicious updates that preserve benign-like statistics while embedding adversarial objectives. Experimental results show that the proposed GRMP attack can substantially decrease accuracy across different LLM models while remaining statistically consistent with benign updates, thereby evading detection by existing defense mechanisms and underscoring a severe threat to the ambitious IoA paradigm.

cs.NI↗

arXiv2025

Auctioning Future Services in Edge Networks with Moving Vehicles: N-Step Look-Ahead Contracts for Sustainable Resource Provision

Timely resource allocation in edge-assisted vehicular networks is essential for compute-intensive services such as autonomous driving and navigation. However, vehicle mobility leads to spatio-temporal unpredictability of resource demands, while real-time double auctions incur significant latency. To address these challenges, we propose a look-ahead contract-based auction framework that shifts decision-making from runtime to planning time. Our approach establishes N-step service contracts between edge servers (ESs) using demand forecasts and modified double auctions. The system operates in two stages: first, an LSTM-based prediction module forecasts multi-slot resource needs and determines ES roles (buyer or seller), after which a pre-double auction generates contracts specifying resource quantities, prices, and penalties. Second, these contracts are enforced in real time without rerunning auctions. The framework incorporates energy costs, transmission overhead, and contract breach risks into utility models, ensuring truthful, rational, and energy-efficient trading. Experiments on real-world (UTD19) and synthetic traces demonstrate that our method improves time efficiency, energy use, and social welfare compared with existing baselines.

eess.SY↗

arXiv2025

PAST: Pilot and Adaptive Orchestration for Timely and Resilient Service Delivery in Edge-Assisted UAV Networks under Spatio-Temporal Dynamics

Incentive-driven resource trading is essential for uncrewed aerial vehicle (UAV) applications with intensive, time-sensitive computing demands. Traditional spot trading suffers from negotiation delays and high energy costs, while conventional futures trading struggles to adapt to the dynamic, uncertain UAV-edge environment. To address these challenges, we propose PAST (pilot-and-adaptive stable trading), a novel framework for edge-assisted UAV networks with spatio-temporal dynamism. PAST integrates two complementary mechanisms: PilotAO (pilot trading agreements with overbooking), a risk-aware, overbooking-enabled early-stage decision-making module that establishes long-term, mutually beneficial agreements and boosts resource utilization; and AdaptAO (adaptive trading agreements with overbooking rate update), an intelligent adaptation module that dynamically updates agreements and overbooking rates based on UAV mobility, supply-demand variations, and agreement performance. Together, these mechanisms integrate stable advance agreement construction with execution-feedback-driven adaptive renewal. Under the stated modeling assumptions, PilotAO satisfies the adopted individual-rationality and strong-stability criteria, as well as the competitive equilibrium and weak Pareto properties established for the considered trading model. Comprehensive experiments further demonstrate that, by coordinating advance planning with selective agreement renewal, PAST effectively balances stability, adaptability, and decision-making efficiency under dynamic UAV-edge conditions.

cs.DC↗

arXiv2025

Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things

This paper focuses on Zero-Trust Foundation Models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet of Things (IoT) systems. By integrating core tenets, such as continuous verification, least privilege access (LPA), data confidentiality, and behavioral analytics into the design, training, and deployment of FMs, ZTFMs can enable secure, privacy-preserving AI across distributed, heterogeneous, and potentially adversarial IoT environments. We present the first structured synthesis of ZTFMs, identifying their potential to transform conventional trust-based IoT architectures into resilient, self-defending ecosystems. Moreover, we propose a comprehensive technical framework, incorporating federated learning (FL), blockchain-based identity management, micro-segmentation, and trusted execution environments (TEEs) to support decentralized, verifiable intelligence at the network edge. In addition, we investigate emerging security threats unique to ZTFM-enabled systems and evaluate countermeasures, such as anomaly detection, adversarial training, and secure aggregation. Through this analysis, we highlight key open research challenges in terms of scalability, secure orchestration, interpretable threat attribution, and dynamic trust calibration. This survey lays a foundational roadmap for secure, intelligent, and trustworthy IoT infrastructures powered by FMs.

cs.CR↗

arXiv2025

Undermining Federated Learning Accuracy in EdgeIoT via Variational Graph Auto-Encoders

EdgeIoT represents an approach that brings together mobile edge computing with Internet of Things (IoT) devices, allowing for data processing close to the data source. Sending source data to a server is bandwidth-intensive and may compromise privacy. Instead, federated learning allows each device to upload a shared machine-learning model update with locally processed data. However, this technique, which depends on aggregating model updates from various IoT devices, is vulnerable to attacks from malicious entities that may inject harmful data into the learning process. This paper introduces a new attack method targeting federated learning in EdgeIoT, known as data-independent model manipulation attack. This attack does not rely on training data from the IoT devices but instead uses an adversarial variational graph auto-encoder (AV-GAE) to create malicious model updates by analyzing benign model updates intercepted during communication. AV-GAE identifies and exploits structural relationships between benign models and their training data features. By manipulating these structural correlations, the attack maximizes the training loss of the federated learning system, compromising its overall effectiveness.

cs.LG↗

arXiv2025

Future Resource Bank for ISAC: Achieving Fast and Stable Win-Win Matching for Both Individuals and Coalitions

Future wireless networks must support emerging applications where environmental awareness is as critical as data transmission. Integrated Sensing and Communication (ISAC) enables this vision by allowing base stations (BSs) to allocate bandwidth and power to mobile users (MUs) for communications and cooperative sensing. However, this resource allocation is highly challenging due to: (i) dynamic resource demands from MUs and resource supply from BSs, and (ii) the selfishness of MUs and BSs. To address these challenges, existing solutions rely on either real-time (online) resource trading, which incurs high overhead and failures, or static long-term (offline) resource contracts, which lack flexibility. To overcome these limitations, we propose the Future Resource Bank for ISAC, a hybrid trading framework that integrates offline and online resource allocation through a level-wise client model, where MUs and their coalitions negotiate with BSs. We introduce two mechanisms: (i) Role-Friendly Win-Win Matching (offRFW$^2$M), leveraging overbooking to establish risk-aware, stable contracts, and (ii) Effective Backup Win-Win Matching (onEBW$^2$M), which dynamically reallocates unmet demand and surplus supply. We theoretically prove stability, individual rationality, and weak Pareto optimality of these mechanisms. Through simulations, we show that our framework improves social welfare, latency, and energy efficiency compared to existing methods.

cs.DC↗

arXiv2022

Break The Spell Of Total Correlation In betaTCVAE

In the absence of artificial labels, the independent and dependent features in the data are cluttered. How to construct the inductive biases of the model to flexibly divide and effectively contain features with different complexity is the main focal point of unsupervised disentangled representation learning. This paper proposes a new iterative decomposition path of total correlation and explains the disentangled representation ability of VAE from the perspective of model capacity allocation. The newly developed objective function combines latent variable dimensions into joint distribution while relieving the independence constraints of marginal distributions in combination, leading to latent variables with a more manipulable prior distribution. The novel model enables VAE to adjust the parameter capacity to divide dependent and independent data features flexibly. Experimental results on various datasets show an interesting relevance between model capacity and the latent variable grouping size, called the "V"-shaped best ELBO trajectory. Additionally, we empirically demonstrate that the proposed method obtains better disentangling performance with reasonable parameter capacity allocation.

cs.LG↗