arXiv subjects

Xiaoyu Xia

Publications and source records attributed to Xiaoyu Xia.

At least 19 recordsLinked to original sources

arXiv2026

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existing RLVR methods typically rely on final-answer correctness to assign trajectory-level rewards, providing sparse supervision and treating all tokens uniformly regardless of their actual contribution to reasoning. Although recent studies introduce intermediate signals such as process rewards, high-entropy tokens, and semantic uncertainty, these signals are often not inherently verifiable and may fail to distinguish beneficial strategic patterns from harmful ones. To address this limitation, we propose STRIDE (Strategic Trajectory Reasoning with Discriminative Estimation), a fine-grained RLVR framework that derives strategic reasoning supervision from verifiable outcomes. STRIDE contrasts successful and failed trajectories within each response group to estimate the outcome-discriminative preference of each $n$-gram strategic pattern, and further combines this signal with reasoning saliency entropy to identify decision-relevant strategic patterns. These patterns are assigned differentiated advantage values during RL optimization, enabling more precise credit assignment while preserving the verifiability of RLVR. Extensive experiments demonstrate that STRIDE consistently improves reasoning performance across diverse models, tasks, and extended settings, including VLMs and agent-based systems.

cs.AI↗

arXiv2026

CoRe-Code: Collaborative Reinforcement Learning for Code Generation

Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing test cases or inefficient complexity). While recent approaches such as Chain-of-Thought (CoT) and multi-agent systems (MAS) introduce planning, their limited role specialization and coordination hinder performance on complex tasks. To address the challenges of coordination and specialization in multi-agent code generation, we propose Collaborative Reinforcement Code (CoRe-Code), a framework for role specialized LLM agents that enhances inter-agent coordination to generate more accurate and efficient code. CoRe-Code adopts a simple Planner-Coder paradigm, where the Planner produces high-level plans and the Coder executes them to generate code. We further introduce a collaboration-aware reinforcement learning stage based on Group Relative Policy Optimization (GRPO) to enhance role specialization and alignment. Experiments show that CoRe-Code outperforms a wide range of existing RL-based and multi-agent methods. In addition, we demonstrate that CoRe-Code can generalize to other multi-agent frameworks (e.g., Retrieval and Debugging agents), highlighting its flexibility and scalability. We evaluate CoRe-Code on multiple benchmarks of varying difficulty using three base models. Compared to existing baselines, the results show consistent improvements in accuracy, while also achieving higher efficiency in terms of execution time and memory usage, demonstrating the effectiveness and practicality of CoRe-Code.

cs.AI↗

arXiv2026

SoK: Unlearnability and Unlearning for Model Dememorization

Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learning (ML). At the training stage, unlearnability embeds imperceptible perturbations into data before release to reduce learnability. At the post-training stage, unlearning removes previously acquired information from models to prevent unauthorized disclosure or use. While both defenses aim to preserve the right to withhold knowledge, their vulnerabilities and shared foundations remain unclear. Specifically, both unlearnability and unlearning suffer from issues such as shallow dememorization, leading to falsely claimed data learnability reduction or forgetting in the presence of weight perturbations. Moreover, input perturbations may affect the effectiveness of downstream unlearning, while unlearning may inadvertently recover domain knowledge hidden by unlearnability. This interplay calls for deeper investigation. Finally, there is a lack of formal guarantees to provide theoretical insights into current defenses against shallow dememorization. In this Systematization of Knowledge, we present the first integrated analysis of model dememorization approaches leveraging unlearnability and unlearning. Our contributions are threefold: (i) a unified taxonomy of unlearnability and scalable unlearning methods; (ii) an empirical evaluation revealing the robustness, interplay, and shallow dememorization of leading methods; and (iii) the first theoretical guarantee on dememorization depth for models processed through certified unlearning. These results lay the foundation for unifying dememorization mechanisms across the ML lifecycle to achieve a deeper immemor state for sensitive knowledge.

cs.LG↗

arXiv2026

Zero-Trust Bilateral Edge Service Trading with Deposit-Refund Regulation for Runtime Compliance

Privacy-sensitive edge services necessitate optimizing diverse-type resource scheduling to support trustworthy provisioning within a zero-trust security framework. However, existing studies rarely model how runtime compliance jointly affects bilateral clearing, ex-post settlement, and future seller eligibility in dynamic edge markets. To address this issue, we propose ZEBRIS, a zero-trust bilateral edge service trading framework with deposit-refund regulation for privacy-sensitive services. Specifically, edge provisioning is modeled as a trading form of zero-trust-compliant service packages, where the buyer-side effective valuation captures service value, delay penalty, and privacy risk, while the seller-side effective ask incorporates resource and compliance costs. This yields a resource-aware positive-margin bilateral clearing mechanism under shared resource and security constraints. To discipline post-clearing moral hazard, we further design a capped deposit-refund settlement rule based on measurable runtime compliance and update each seller's future security posture according to realized compliance outcomes. ZEBRIS satisfies bilateral individual rationality and no-subsidy weak budget balance. Experiments demonstrate that ZEBRIS improves social welfare and compliance robustness while reducing service delay and privacy-risk-weighted cost over representative baselines.

cs.NI↗

arXiv2026

Safe Multi-Agent Deep Reinforcement Learning for Privacy-Aware Edge-Device Collaborative DNN Inference

As Deep Neural Network (DNN) inference becomes increasingly prevalent on edge and mobile platforms, critical challenges emerge in privacy protection, resource constraints, and dynamic model deployment. This paper proposes a privacy-aware collaborative inference framework, in which adaptive model partitioning is performed across edge devices and servers. To jointly optimize inference delay, energy consumption, and privacy cost under dynamic service demands and resource constraints, we formulate the joint problem as a Constrained Markov Decision Process (CMDP) that integrates model deployment, user-server association, model partitioning, and resource allocation. We propose a Hierarchical Constrained Multi-Agent Proximal Policy Optimization with Lagrangian relaxation (HC-MAPPO-L) algorithm, a safe reinforcement learning-based framework that enhances Multi-Agent Proximal Policy Optimization (MAPPO) with adaptive Lagrangian dual updates to enforce long-term delay constraints. To ensure tractability while maintaining coordination, we decompose the CMDP into three hierarchically structured policy layers: an auto-regressive based model deployment policy, a Lagrangian-enhanced user association and model partitioning policy, and an attention-based resource allocation policy. Extensive experimental results demonstrate that HC-MAPPO-L consistently satisfies stringent delay constraints while achieving a superior balance among energy consumption and privacy cost, outperforming representative baseline algorithms across varying problem scales and resource configurations.

cs.MA↗

arXiv2026

WinFLoRA: Incentivizing Client-Adaptive Aggregation in Federated LoRA under Privacy Heterogeneity

Large Language Models (LLMs) increasingly underpin intelligent web applications, from chatbots to search and recommendation, where efficient specialization is essential. Low-Rank Adaptation (LoRA) enables such adaptation with minimal overhead, while federated LoRA allows web service providers to fine-tune shared models without data sharing. However, in privacy-sensitive deployments, clients inject varying levels of differential privacy (DP) noise, creating privacy heterogeneity that misaligns individual incentives and global performance. In this paper, we propose WinFLoRA, a privacy-heterogeneous federated LoRA that utilizes aggregation weights as incentives with noise awareness. Specifically, the noises from clients are estimated based on the uploaded LoRA adapters. A larger weight indicates greater influence on the global model and better downstream task performance, rewarding lower-noise contributions. By up-weighting low-noise updates, WinFLoRA improves global accuracy while accommodating clients' heterogeneous privacy requirements. Consequently, WinFLoRA aligns heterogeneous client utility in terms of privacy and downstream performance with global model objectives without third-party involvement. Extensive evaluations demonstrate that across multiple LLMs and datasets, WinFLoRA achieves up to 52.58% higher global accuracy and up to 2.56x client utility than state-of-the-art benchmarks. Source code is publicly available at https://github.com/koums24/WinFLoRA.git.

cs.LG↗

arXiv2025

Game-Theoretic Safe Multi-Agent Motion Planning with Reachability Analysis for Dynamic and Uncertain Environments (Extended Version)

Ensuring safe, robust, and scalable motion planning for multi-agent systems in dynamic and uncertain environments is a persistent challenge, driven by complex inter-agent interactions, stochastic disturbances, and model uncertainties. To overcome these challenges, particularly the computational complexity of coupled decision-making and the need for proactive safety guarantees, we propose a Reachability-Enhanced Dynamic Potential Game (RE-DPG) framework, which integrates game-theoretic coordination into reachability analysis. This approach formulates multi-agent coordination as a dynamic potential game, where the Nash equilibrium (NE) defines optimal control strategies across agents. To enable scalability and decentralized execution, we develop a Neighborhood-Dominated iterative Best Response (ND-iBR) scheme, built upon an iterated $\varepsilon$-BR (i$\varepsilon$-BR) process that guarantees finite-step convergence to an $\varepsilon$-NE. This allows agents to compute strategies based on local interactions while ensuring theoretical convergence guarantees. Furthermore, to ensure safety under uncertainty, we integrate a Multi-Agent Forward Reachable Set (MA-FRS) mechanism into the cost function, explicitly modeling uncertainty propagation and enforcing collision avoidance constraints. Through both simulations and real-world experiments in 2D and 3D environments, we validate the effectiveness of RE-DPG across diverse operational scenarios.

cs.RO↗

arXiv2025

Tunable Hybrid-Mode Coupler Enabling Strong Interactions between Transmons at Centimeter-Scale Distance

The transmon, a fabrication-friendly superconducting qubit, remains a leading candidate for scalable quantum computing. Recent advances in tunable couplers have accelerated progress toward high-performance quantum processors. However, extending coherent interactions beyond millimeter scales to enhance quantum connectivity presents a critical challenge. Here, we introduce a hybrid-mode coupler exploiting resonator-transmon hybridization to simultaneously engineer the two lowest-frequency mode, enabling high-contrast coupling between centimeter-scale transmons. For a 1-cm coupler, our framework predicts flux-tunable $XX$ and $ZZ$ coupling strengths reaching 23 MHz and 100 MHz, with modulation contrasts exceeding $10^2$ and $10^4$, respectively, demonstrating quantitative agreement with an effective two-channel model. This work provides an efficient pathway to mitigate the inherent connectivity constraints imposed by short-range interactions, enabling transmon-based architectures compatible with hardware-efficient quantum tasks.

quant-ph↗

arXiv2025

Effective Two-Stage Double Auction for Dynamic Resource Provision over Edge Networks via Discovering The Power of Overbooking

To facilitate responsive and cost-effective computing service delivery over edge networks, this paper investigates a novel two-stage double auction methodology via discovering an interesting idea of resource overbooking to overcome dynamic and uncertain nature of supply of edge servers (sellers) and demand generated from mobile devices (as buyers). The proposed auction integrates multiple essential goals such as maximizing social welfare as well as accelerating the decision-making process from both short-term and long-term views, (e.g., the time for determining winning seller-buyer pairs), by introducing a stagewise strategy: an overbooking-driven pre-double auction (OPDAuction) for determining long-term cooperations between sellers and buyers before practical resource transactions as Stage I, and a real-time backup double auction (RBDAuction) for quickly coping with residual resource demands during actual transactions. In particular, by embedding a proper overbooking rate, OPDAuction helps with facilitating trading contracts between appropriate sellers and buyers as guidance for future transactions, by allowing the booked resources to exceed theoretical supply. Then, since pre-auctions may cause risks, our RBDAuction adjusts to real-time market changes, further enhancing the overall social welfare. More importantly, we offer an interesting view to show that our proposed two-stage auction can support significant design properties such as truthfulness, individual rationality, and budget balance. Through extensive experiments, we demonstrate good performance in social welfare, time efficiency, and computational scalability, outstripping conventional methods in dynamic edge computing settings.

cs.GT↗

arXiv2025

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks

Spiking Neural Networks (SNNs) have gained increasing attention for their superior energy efficiency compared to Artificial Neural Networks (ANNs). However, their security aspects, particularly under backdoor attacks, have received limited attention. Existing defense methods developed for ANNs perform poorly or can be easily bypassed in SNNs due to their event-driven and temporal dependencies. This paper identifies the key blockers that hinder traditional backdoor defenses in SNNs and proposes an unsupervised post-training detection framework, Temporal Membrane Potential Backdoor Detection (TMPBD), to overcome these challenges. TMPBD leverages the maximum margin statistics of temporal membrane potential (TMP) in the final spiking layer to detect target labels without any attack knowledge or data access. We further introduce a robust mitigation mechanism, Neural Dendrites Suppression Backdoor Mitigation (NDSBM), which clamps dendritic connections between early convolutional layers to suppress malicious neurons while preserving benign behaviors, guided by TMP extracted from a small, clean, unlabeled dataset. Extensive experiments on multiple neuromorphic benchmarks and state-of-the-art input-aware dynamic trigger attacks demonstrate that TMPBD achieves 100% detection accuracy, while NDSBM reduces the attack success rate from 100% to 8.44%, and to 2.81% when combined with detection, without degrading clean accuracy.

cs.CR↗

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

Oh-Trust: Overbooking and Hybrid Trading-empowered Resource Scheduling with Smart Reputation Update over Dynamic Edge Networks

Incentive-driven computing resource sharing is crucial for meeting the ever-growing demands of emerging mobile applications. Although conventional spot trading offers a solution, it frequently leads to excessive overhead due to the need for real-time trading related interactions. Likewise, traditional futures trading, which depends on historical data, is susceptible to risks from network dynamics. This paper explores a dynamic and uncertain edge network comprising a computing platform, e.g., an edge server, that offers computing services as resource seller, and various types of mobile users with diverse resource demands as buyers, including fixed buyers (FBs) and uncertain occasional buyers (OBs) with fluctuating needs. To facilitate efficient and timely computing services, we propose an overbooking- and hybrid trading-empowered resource scheduling mechanism with reputation update, termed Oh-Trust. Particularly, our Oh-Trust incentivizes FBs to enter futures trading by signing long-term contracts with the seller, while simultaneously attracting OBs to spot trading, enhancing resource utilization and profitability for both parties. Crucially, to adapt to market fluctuations, a smart reputation updating mechanism is integrated, allowing for the timely renewal of long-term contracts to optimize trading performance. Extensive simulations using real-world datasets demonstrate the effectiveness of Oh-Trust across multiple evaluation metrics.

cs.NI↗

arXiv2025

MPOCryptoML: Multi-Pattern based Off-Chain Crypto Money Laundering Detection

Recent advancements in money laundering detection have demonstrated the potential of using graph neural networks to capture laundering patterns accurately. However, existing models are not explicitly designed to detect the diverse patterns of off-chain cryptocurrency money laundering. Neglecting any laundering pattern introduces critical detection gaps, as each pattern reflects unique transactional structures that facilitate the obfuscation of illicit fund origins and movements. Failure to account for these patterns may result in under-detection or omission of specific laundering activities, diminishing model accuracy and allowing schemes to bypass detection. To address this gap, we propose the MPOCryptoML model to effectively detect multiple laundering patterns in cryptocurrency transactions. MPOCryptoML includes the development of a multi-source Personalized PageRank algorithm to identify random laundering patterns. Additionally, we introduce two novel algorithms by analyzing the timestamp and weight of transactions in high-volume financial networks to detect various money laundering structures, including fan-in, fan-out, bipartite, gather-scatter, and stack patterns. We further examine correlations between these patterns using a logistic regression model. An anomaly score function integrates results from each module to rank accounts by anomaly score, systematically identifying high-risk accounts. Extensive experiments on public datasets including Elliptic++, Ethereum fraud detection, and Wormhole transaction datasets validate the efficacy and efficiency of MPOCryptoML. Results show consistent performance gains, with improvements up to 9.13% in precision, up to 10.16% in recall, up to 7.63% in F1-score, and up to 10.19% in accuracy.

cs.CR↗

arXiv2025

Slow is Fast! Dissecting Ethereum's Slow Liquidity Drain Scams

We identify the slow liquidity drain (SLID) scam, an insidious and highly profitable threat to decentralized finance (DeFi), posing a large-scale, persistent, and growing risk to the ecosystem. Unlike traditional scams such as rug pulls or honeypots (USENIX Sec'19, USENIX Sec'23), SLID gradually siphons funds from liquidity pools over extended periods, making detection significantly more challenging. In this paper, we conducted the first large-scale empirical analysis of 319,166 liquidity pools across six major decentralized exchanges (DEXs) since 2018. We identified 3,117 SLID affected liquidity pools, resulting in cumulative losses of more than US$103 million. We propose a rule-based heuristic and an enhanced machine learning model for early detection. Our machine learning model achieves a detection speed 4.77 times faster than the heuristic while maintaining 95% accuracy. Our study establishes a foundation for protecting DeFi investors at an early stage and promoting transparency in the DeFi ecosystem.

cs.CR↗

arXiv2025

Edge Association Strategies for Synthetic Data Empowered Hierarchical Federated Learning with Non-IID Data

In recent years, Federated Learning (FL) has emerged as a widely adopted privacy-preserving distributed training approach, attracting significant interest from both academia and industry. Research efforts have been dedicated to improving different aspects of FL, such as algorithm improvement, resource allocation, and client selection, to enable its deployment in distributed edge networks for practical applications. One of the reasons for the poor FL model performance is due to the worker dropout during training as the FL server may be located far away from the FL workers. To address this issue, an Hierarchical Federated Learning (HFL) framework has been introduced, incorporating an additional layer of edge servers to relay communication between the FL server and workers. While the HFL framework improves the communication between the FL server and workers, large number of communication rounds may still be required for model convergence, particularly when FL workers have non-independent and identically distributed (non-IID) data. Moreover, the FL workers are assumed to fully cooperate in the FL training process, which may not always be true in practical situations. To overcome these challenges, we propose a synthetic-data-empowered HFL framework that mitigates the statistical issues arising from non-IID local datasets while also incentivizing FL worker participation. In our proposed framework, the edge servers reward the FL workers in their clusters for facilitating the FL training process. To improve the performance of the FL model given the non-IID local datasets of the FL workers, the edge servers generate and distribute synthetic datasets to FL workers within their clusters. FL workers determine which edge server to associate with, considering the computational resources required to train on both their local datasets and the synthetic datasets.

cs.DC↗

arXiv2025

Fabrication of airbridges with gradient exposure

In superconducting quantum circuits, airbridges are critical for eliminating parasitic slotline modes of coplanar waveguide circuits and reducing crosstalks between direct current magnetic flux biases. Here, we present a technique for fabricating superconducting airbridges. With this technique, a single layer of photoresist is employed, and the gradient exposure process is used to define the profile of airbridges. In order to properly obtain the bridge profile, we design exposure dosage based on residual photoresist thickness and laser power calibrations. Compared with other airbridge fabrication techniques, the gradient exposure fabrication technique provides the ability to produce lossless superconducting airbridges with flexible size and, thus, is more suitable for large-scale superconducting quantum circuits. Furthermore, this method reduces the complexity of the fabrication process and provides a high fabrication yield.

quant-ph↗

arXiv2025

Privacy-Aware Joint DNN Model Deployment and Partitioning Optimization for Collaborative Edge Inference Services

Edge inference (EI) has emerged as a promising paradigm to address the growing limitations of cloud-based Deep Neural Network (DNN) inference services, such as high response latency, limited scalability, and severe data privacy exposure. However, deploying DNN models on resource-constrained edge devices introduces additional challenges, including limited computation/storage resources, dynamic service demands, and heightened privacy risks. To tackle these issues, this paper presents a novel privacy-aware optimization framework that jointly addresses DNN model deployment, user-server association, and model partitioning, with the goal of minimizing long-term average inference delay under resource and privacy constraints. The problem is formulated as a complex, NP-hard stochastic optimization. To efficiently handle system dynamics and computational complexity, we employ a Lyapunov-based approach to transform the long-term objective into tractable per-slot decisions. Furthermore, we introduce a coalition formation game to enable adaptive user-server association and design a greedy algorithm for model deployment within each coalition. Extensive simulations demonstrate that the proposed algorithm significantly reduces inference delay and consistently satisfies privacy constraints, outperforming state-of-the-art baselines across diverse scenarios.

cs.LG↗

arXiv2025

Seamless Graph Task Scheduling over Dynamic Vehicular Clouds: A Hybrid Methodology for Integrating Pilot and Instantaneous Decisions

Vehicular clouds (VCs) play a crucial role in the Internet-of-Vehicles (IoV) ecosystem by securing essential computing resources for a wide range of tasks. This paPertackles the intricacies of resource provisioning in dynamic VCs for computation-intensive tasks, represented by undirected graphs for parallel processing over multiple vehicles. We model the dynamics of VCs by considering multiple factors, including varying communication quality among vehicles, fluctuating computing capabilities of vehicles, uncertain contact duration among vehicles, and dynamic data exchange costs between vehicles. Our primary goal is to obtain feasible assignments between task components and nearby vehicles, called templates, in a timely manner with minimized task completion time and data exchange overhead. To achieve this, we propose a hybrid graph task scheduling (P-HTS) methodology that combines offline and online decision-making modes. For the offline mode, we introduce an approach called risk-aware pilot isomorphic subgraph searching (RA-PilotISS), which predicts feasible solutions for task scheduling in advance based on historical information. Then, for the online mode, we propose time-efficient instantaneous isomorphic subgraph searching (TE-InstaISS), serving as a backup approach for quickly identifying new optimal scheduling template when the one identified by RA-PilotISS becomes invalid due to changing conditions. Through comprehensive experiments, we demonstrate the superiority of our proposed hybrid mechanism compared to state-of-the-art methods in terms of various evaluative metrics, e.g., time efficiency such as the delay caused by seeking for possible templates and task completion time, as well as cost function, upon considering different VC scales and graph task topologies.

cs.NI↗