arXiv subjects

Kang Wei

Publications and source records attributed to Kang Wei.

At least 19 recordsLinked to original sources

arXiv2026

Low-Latency Federated Fine-Tuning for Large Language Models Over Wireless Networks

Recently, federated large language models (LLMs) have drawn significant attention thanks to coupled capabilities of LLMs and federated learning (FL) that address privacy concerns in collaborative fine-tuning. However, due to large-scale parameters of LLMs, existing federated LLM fine-tuning frameworks incur significant challenges in resource-constrained clients characterized by heterogeneous computing capabilities and random wireless channels. To address this issue, we propose a joint client-specific pruning and bandwidth allocation (JCPBA) framework for federated LLMs to improve the fine-tuning efficiency over the wireless networks. Specifically, we formulate a fine-tuning latency minimization problem by jointly optimizing pruning rates and bandwidth allocations. Furthermore, we solve this optimization problem using a block coordinate descent method. Extensive experiments on the datasets of Yahoo Answers and GSM8K demonstrate that the proposed framework significantly reduces wall-clock fine-tuning time compared with state-of-the-art baselines and gains equal or lower test loss at the cost of lower computation and communication overhead.

cs.DC↗

arXiv2025

Fragmentation of neutron-rich carbon isotopes on light targets at 27.5 MeV/nucleon

Experimental and theoretical investigation of the fragmentation reaction in Fermi-energy domain is currently of particular importance for not only the nuclear physics but also some interdisciplinary fields. In the present work, neutron-rich $^{14}$C and $^{16}$C ion beams at 27.5 MeV/nucleon were used to bombard carbon and polyethylene (CD$_{2}$)$_{n}$ targets. Energy and angular distributions of the produced fragments were measured. Background events originating from the carbon content in (CD$_{2}$)$_{n}$ target were efficiently excluded using an extended $E-P$ plot method. Experimental results are systematically analyzed by using HIPSE-SIMON dynamic model. The comparison reveals that, for the carbon target, the HIPSE-SIMON calculation overestimates the yields of the beam-velocity component for fragments near the projectile and also the energy phase space for fragments far away from the projectile, suggesting fine tuning of the overall interaction profile adopted in the model. In contrast, for reactions with the deuteron target, the model calculation can reasonably reproduce the experimental data. The implication of the fragmentation mechanism to the validity of the invariant mass method, as frequently used to reconstruct the clustering resonant structures in light nuclei, is also discussed.

nucl-ex↗

arXiv2025

Stable-MoE: Lyapunov-based Token Routing for Distributed Mixture-of-Experts Training over Edge Networks

The sparse activation mechanism of mixture of experts (MoE) model empowers edge intelligence with enhanced training efficiency and reduced computational resource consumption. However, traditional token routing in distributed MoE training faces significant challenges in resource-constrained edge networks characterized by heterogeneous computing capabilities and stochastic token arrivals, which inevitably suffer from workload backlog, resource inefficiency, and performance degradation. To address this issue, we propose a novel Lyapunov-based token routing framework for distributed MoE training over resource-heterogeneous edge networks, termed Stable-MoE. Specifically, we formulate a stochastic optimization problem to maximize both system throughput and gating consistency via optimizing the token routing strategy and computational resource allocation, while ensuring long-term stability of both token and energy queues at the edge devices. Using the Lyapunov optimization, we transform the intractable long-term optimization problem into tractable per-slot subproblems by enabling online decision-making of token routing and computation frequency utilization without the knowledge of future system states. Experimental results on the SVHN and CIFAR-100 datasets demonstrate that Stable-MoE outperforms the baselines with at least 40% and 5% gains in system throughput and test accuracy, respectively.

cs.DC↗

arXiv2025

Rotatable Antenna Meets UAV: Towards Dual-Level Channel Reconfiguration Paradigm for ISAC

Integrated sensing and communication (ISAC) is viewed as a key enabler for future wireless networks by sharing the hardware and wireless resources between the functionalities of sensing and communication (S&C). Due to the shared wireless resources for both S&C, it is challenging to achieve a critical trade-off between these two integrated functionalities. To address this issue, this paper proposes a novel dual-level channel reconfiguration framework for ISAC by deploying rotatable antennas at an unmanned aerial vehicle (UAV), where both the large-scale path loss and the correlation of S&C channels can be proactively controlled, thereby allowing a flexible trade-off between S&C performance. To characterize the S&C tradeoff, we aim to maximize the communication rate by jointly optimizing the RA rotation, the transmit beamforming, and the UAV trajectory, subject to the given requirement of sensing performance. For the typical scenario of static UAV deployment, we introduce the concept of subspace correlation coefficient to derive closed-form solutions for the optimal RA rotation, transmit beamforming, and UAV hovering location. For the scenario of a fully mobile UAV, we prove that the optimal trajectory of a UAV follows a hover-fly-hover (HFH) structure, thereby obtaining its global optimal solution. Simulation results show that the proposed design significantly improves the achievable S&C trade-off region compared to benchmark schemes.

cs.IT↗

arXiv2025

Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models

Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential threats to DMs. To provide advanced and comprehensive insights into safety, ethics, and trust in DMs, this survey comprehensively elucidates its framework, threats, and countermeasures. Each threat and its countermeasures are systematically examined and categorized to facilitate thorough analysis. Furthermore, we introduce specific examples of how DMs are used, what dangers they might bring, and ways to protect against these dangers. Finally, we discuss key lessons learned, highlight open challenges related to DM security, and outline prospective research directions in this critical field. This work aims to accelerate progress not only in the technical capabilities of generative artificial intelligence but also in the maturity and wisdom of its application.

cs.CR↗

arXiv2025

Analysis and Optimization of Wireless Multimodal Federated Learning on Modal Heterogeneity

Multimodal federated learning (MFL) is a distributed framework for training multimodal models without uploading local multimodal data of clients, thereby effectively protecting client privacy. However, multimodal data is commonly heterogeneous across diverse clients, where each client possesses only a subset of all modalities, renders conventional analysis results and optimization methods in unimodal federated learning inapplicable. In addition, fixed latency demand and limited communication bandwidth pose significant challenges for deploying MFL in wireless scenarios. To optimize the wireless MFL performance on modal heterogeneity, this paper proposes a joint client scheduling and bandwidth allocation (JCSBA) algorithm based on a decision-level fusion architecture with adding a unimodal loss function. Specifically, with the decision results, the unimodal loss functions are added to both the training objective and local update loss functions to accelerate multimodal convergence and improve unimodal performance. To characterize MFL performance, we derive a closed-form upper bound related to client and modality scheduling and minimize the derived bound under the latency, energy, and bandwidth constraints through JCSBA. Experimental results on multimodal datasets demonstrate that the JCSBA algorithm improves the multimodal accuracy and the unimodal accuracy by 4.06% and 2.73%, respectively, compared to conventional algorithms.

cs.DC↗

arXiv2025

When MoE Meets Blockchain: A Trustworthy Distributed Framework of Large Models

As an enabling architecture of Large Models (LMs), Mixture of Experts (MoE) has become prevalent thanks to its sparsely-gated mechanism, which lowers computational overhead while maintaining learning performance comparable to dense LMs. The essence of MoE lies in utilizing a group of neural networks (called experts) with each specializing in different types of tasks, along with a trainable gating network that selectively activates a subset of these experts to handle specific tasks. Traditional cloud-based MoE encounters challenges such as prolonged response latency, high bandwidth consumption, and data privacy leakage. To address these issues, researchers have proposed to deploy MoE over distributed edge networks. However, a key concern of distributed MoE frameworks is the lack of trust in data interactions among distributed experts without the surveillance of any trusted authority, and thereby prone to potential attacks such as data manipulation. In response to the security issues of traditional distributed MoE, we propose a blockchain-aided trustworthy MoE (B-MoE) framework that consists of three layers: the edge layer, the blockchain layer, and the storage layer. In this framework, the edge layer employs the activated experts downloaded from the storage layer to process the learning tasks, while the blockchain layer functions as a decentralized trustworthy network to trace, verify, and record the computational results of the experts from the edge layer. The experimental results demonstrate that B-MoE is more robust to data manipulation attacks than traditional distributed MoE during both the training and inference processes.

cs.DC↗

arXiv2025

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning

Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making applications, including robotics, healthcare, smart grids, and finance. Recent studies reveal that adversaries can implant backdoors into DRL agents during the training phase. These backdoors can later be activated by specific triggers during deployment, compelling the agent to execute targeted actions and potentially leading to severe consequences, such as drone crashes or vehicle collisions. However, existing backdoor attacks utilize simplistic and heuristic trigger configurations, overlooking the critical impact of trigger design on attack effectiveness. To address this gap, we introduce TooBadRL, the first framework to systematically optimize DRL backdoor triggers across three critical aspects: injection timing, trigger dimension, and manipulation magnitude. Specifically, we first introduce a performance-aware adaptive freezing mechanism to determine the injection timing during training. Then, we formulate trigger selection as an influence attribution problem and apply Shapley value analysis to identify the most influential trigger dimension for injection. Furthermore, we propose an adversarial input synthesis method to optimize the manipulation magnitude under environmental constraints. Extensive evaluations on three DRL algorithms and nine benchmark tasks demonstrate that TooBadRL outperforms five baseline methods in terms of attack success rate while only slightly affecting normal task performance. We further evaluate potential defense strategies from detection and mitigation perspectives. We open-source our code to facilitate reproducibility and further research.

cs.CR↗

arXiv2024

DNN-based Enhanced DOA Sensing via Massive MIMO Receiver with Switches-based Hybrid Architecture

Switches-based hybrid architecture has attracted much attention, especially in directional-of-arrival (DOA) sensing, due to its ability of significantly reducing the hardware cost by compressing massive multiple-input multiple-output (MIMO) arrays with switching networks. However, this structure will lead to a degradation in the degrees of freedom (DOF) and accuracy of DOA estimation. To address these two issues, we first propose a switches-based sparse hybrid array (SW-SHA). In this method, we design a dynamic switching network to form a synthesized sparse array, i.e., SW-SHA, that can enlarge the virtual aperture obtained by the difference co-array, thereby significantly enhancing the DOF. Second, in order to improve the DOA estimation accuracy of switches-based hybrid arrays, a deep neural network (DNN)-based method called ASN-DNN is proposed. It includes an antenna selection network (ASN) for optimizing the switch connections based on the criterion of minimizing the Cramer-Rao lower bound (CRLB) under the peak sidelobe level (PSL) constraint and a DNN for DOA estimation. Then by integrating ASN and DNN into an iterative process, the ASN-DNN is obtained. Furthermore, the closed-form expression of CRLB for DOA estimation is derived to evaluate the performance lower bound of switches-based hybrid arrays and provide a benchmark for ASN-DNN. The simulation results show the proposed ASN-DNN can achieve a greater performance than traditional methods, especially in the low signal-to-noise ratio (SNR) regions.

eess.SP↗

arXiv2024

Resource Efficient Asynchronous Federated Learning for Digital Twin Empowered IoT Network

As an emerging technology, digital twin (DT) can provide real-time status and dynamic topology mapping for Internet of Things (IoT) devices. However, DT and its implementation within industrial IoT networks necessitates substantial, distributed data support, which often leads to ``data silos'' and raises privacy concerns. To address these issues, we develop a dynamic resource scheduling algorithm tailored for the asynchronous federated learning (FL)-based lightweight DT empowered IoT network. Specifically, our approach aims to minimize a multi-objective function that encompasses both energy consumption and latency by optimizing IoT device selection and transmit power control, subject to FL model performance constraints. We utilize the Lyapunov method to decouple the formulated problem into a series of one-slot optimization problems and develop a two-stage optimization algorithm to achieve the optimal transmission power control and IoT device scheduling strategies. In the first stage, we derive closed-form solutions for optimal transmit power on the IoT device side. In the second stage, since partial state information is unknown, e.g., the transmitting power and computational frequency of IoT device, the edge server employs a multi-armed bandit (MAB) framework to model the IoT device selection problem and utilizes an efficient online algorithm, namely the client utility-based upper confidence bound (CU-UCB), to address it. Numerical results validate our algorithm's superiority over benchmark schemes, and simulations demonstrate that our algorithm achieves faster training speeds on the Fashion-MNIST and CIFAR-10 datasets within the same training duration.

cs.DC↗

arXiv2024

Vertical Federated Learning: Challenges, Methodologies and Experiments

Recently, federated learning (FL) has emerged as a promising distributed machine learning (ML) technology, owing to the advancing computational and sensing capacities of end-user devices, however with the increasing concerns on users' privacy. As a special architecture in FL, vertical FL (VFL) is capable of constructing a hyper ML model by embracing sub-models from different clients. These sub-models are trained locally by vertically partitioned data with distinct attributes. Therefore, the design of VFL is fundamentally different from that of conventional FL, raising new and unique research issues. In this paper, we aim to discuss key challenges in VFL with effective solutions, and conduct experiments on real-life datasets to shed light on these issues. Specifically, we first propose a general framework on VFL, and highlight the key differences between VFL and conventional FL. Then, we discuss research challenges rooted in VFL systems under four aspects, i.e., security and privacy risks, expensive computation and communication costs, possible structural damage caused by model splitting, and system heterogeneity. Afterwards, we develop solutions to addressing the aforementioned challenges, and conduct extensive experiments to showcase the effectiveness of our proposed solutions.

cs.LG↗

arXiv2024

Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction

This paper introduces RDA, a pioneering approach designed to address two primary deficiencies prevalent in previous endeavors aiming at stealing pre-trained encoders: (1) suboptimal performances attributed to biased optimization objectives, and (2) elevated query costs stemming from the end-to-end paradigm that necessitates querying the target encoder every epoch. Specifically, we initially Refine the representations of the target encoder for each training sample, thereby establishing a less biased optimization objective before the steal-training phase. This is accomplished via a sample-wise prototype, which consolidates the target encoder's representations for a given sample's various perspectives. Demanding exponentially fewer queries compared to the end-to-end approach, prototypes can be instantiated to guide subsequent query-free training. For more potent efficacy, we develop a multi-relational extraction loss that trains the surrogate encoder to Discriminate mismatched embedding-prototype pairs while Aligning those matched ones in terms of both amplitude and angle. In this way, the trained surrogate encoder achieves state-of-the-art results across the board in various downstream datasets with limited queries. Moreover, RDA is shown to be robust to multiple widely-used defenses.

cs.LG↗

arXiv2024

Machine Learning-based Near-field Emitter Location Sensing via Grouped Hybrid Analog and Digital XL-MIMO Receive Array

As a green MIMO structure, the partially-connected hybrid analog and digital (PC-HAD) structure has been widely used in the far-field (FF) scenario for it can significantly reduce the hardware cost and complexity of large-scale or extremely large-scale MIMO (XL-MIMO) array. Recently, near-field (NF) emitter localization including direction-of-arrival (DOA) and range estimations has drawn a lot of attention, but is rarely explored via PC-HAD structure. In this paper, we first analyze the impact of PC-HAD structure on the NF emitter localization and observe that the phase ambiguity (PA) problem caused by PC-HAD structure can be removed inherently with low-latency in the NF scenario. To obtain the exact NF DOA estimation results, we propose a grouped PC-HAD structure, which is capable of dividing the NF DOA estimation problem into multiple FF DOA estimation problems via partitioning the large-scale PC-HAD array into small-scale groups. An angle calibration method is developed to address the inconsistency among these FF DOA estimation problems. Then, to eliminate PA and improve the NF emitter localization performance, we develop three machine learning (ML)-based methods, i.e., two low-complexity data-driven clustering-based methods and one model-driven regression method, namely RegNet. Furthermore, the Cramer-Rao lower bound (CRLB) of NF emitter localization for the proposed grouped PC-HAD structure is derived and reveals that localization performance will decrease with the increasing of the number of groups. The simulation results show that the proposed methods can achieve CRLB at different SNR regions, the RegNet has great performance advantages at low SNR regions and the clustering-based methods have much lower computation complexity.

eess.SP↗

arXiv2024

Blockchain-aided wireless federated learning: Resource allocation and client scheduling

Federated learning (FL) based on the centralized design faces both challenges regarding the trust issue and a single point of failure. To alleviate these issues, blockchain-aided decentralized FL (BDFL) introduces the decentralized network architecture into the FL training process, which can effectively overcome the defects of centralized architecture. However, deploying BDFL in wireless networks usually encounters challenges such as limited bandwidth, computing power, and energy consumption. Driven by these considerations, a dynamic stochastic optimization problem is formulated to minimize the average training delay by jointly optimizing the resource allocation and client selection under the constraints of limited energy budget and client participation. We solve the long-term mixed integer non-linear programming problem by employing the tool of Lyapunov optimization and thereby propose the dynamic resource allocation and client scheduling BDFL (DRC-BDFL) algorithm. Furthermore, we analyze the learning performance of DRC-BDFL and derive an upper bound for convergence regarding the global loss function. Extensive experiments conducted on SVHN and CIFAR-10 datasets demonstrate that DRC-BDFL achieves comparable accuracy to baseline algorithms while significantly reducing the training delay by 9.24% and 12.47%, respectively.

cs.DC↗

arXiv2024

Trustworthy DNN Partition for Blockchain-enabled Digital Twin in Wireless IIoT Networks

Digital twin (DT) has emerged as a promising solution to enhance manufacturing efficiency in industrial Internet of Things (IIoT) networks. To promote the efficiency and trustworthiness of DT for wireless IIoT networks, we propose a blockchain-enabled DT (B-DT) framework that employs deep neural network (DNN) partitioning technique and reputation-based consensus mechanism, wherein the DTs maintained at the gateway side execute DNN inference tasks using the data collected from their associated IIoT devices. First, we employ DNN partitioning technique to offload the top-layer DNN inference tasks to the access point (AP) side, which alleviates the computation burden at the gateway side and thereby improves the efficiency of DNN inference. Second, we propose a reputation-based consensus mechanism that integrates Proof of Work (PoW) and Proof of Stake (PoS). Specifically, the proposed consensus mechanism evaluates the off-chain reputation of each AP according to its computation resource contributions to the DNN inference tasks, and utilizes the off-chain reputation as a stake to adjust the block generation difficulty. Third, we formulate a stochastic optimization problem of communication resource (i.e., partition point) and computation resource allocation (i.e., computation frequency of APs for top-layer DNN inference and block generation) to minimize system latency under the time-varying channel state and long-term constraints of off-chain reputation, and solve the problem using Lyapunov optimization method. Experimental results show that the proposed dynamic DNN partitioning and resource allocation (DPRA) algorithm outperforms the baselines in terms of reducing the overall latency while guaranteeing the trustworthiness of the B-DT system.

cs.LG↗

arXiv2024

Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization

Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However, federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead compared to federated SGD (FedSGD) algorithms, which arises from the necessity to transmit both local model updates and first and second moment estimates from distributed devices to the centralized server for aggregation. Driven by this issue, we propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates of local model parameters and moment estimates and subsequently upload the sparse representations to the centralized server. To further reduce the communication overhead, the updates of local model parameters and moment estimates incorporate a shared sparse mask (SSM) into the sparsification process, eliminating the need for three separate sparse masks. Theoretically, we develop an upper bound on the divergence between the local model trained by FedAdam-SSM and the desired model trained by centralized Adam, which is related to sparsification error and imbalanced data distribution. By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error. Additionally, we provide convergence bounds for FedAdam-SSM in both convex and non-convex objective function settings, and investigate the impact of local epoch, learning rate and sparsification ratio on the convergence rate of FedAdam-SSM. Experimental results show that FedAdam-SSM outperforms baselines in terms of convergence rate (over 1.1$\times$ faster than the sparse FedAdam baselines) and test accuracy (over 14.5\% ahead of the quantized FedAdam baselines).

cs.LG↗

arXiv2024

EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection

Federated self-supervised learning (FSSL) has recently emerged as a promising paradigm that enables the exploitation of clients' vast amounts of unlabeled data while preserving data privacy. While FSSL offers advantages, its susceptibility to backdoor attacks, a concern identified in traditional federated supervised learning (FSL), has not been investigated. To fill the research gap, we undertake a comprehensive investigation into a backdoor attack paradigm, where unscrupulous clients conspire to manipulate the global model, revealing the vulnerability of FSSL to such attacks. In FSL, backdoor attacks typically build a direct association between the backdoor trigger and the target label. In contrast, in FSSL, backdoor attacks aim to alter the global model's representation for images containing the attacker's specified trigger pattern in favor of the attacker's intended target class, which is less straightforward. In this sense, we demonstrate that existing defenses are insufficient to mitigate the investigated backdoor attacks in FSSL, thus finding an effective defense mechanism is urgent. To tackle this issue, we dive into the fundamental mechanism of backdoor attacks on FSSL, proposing the Embedding Inspector (EmInspector) that detects malicious clients by inspecting the embedding space of local models. In particular, EmInspector assesses the similarity of embeddings from different local models using a small set of inspection images (e.g., ten images of CIFAR100) without specific requirements on sample distribution or labels. We discover that embeddings from backdoored models tend to cluster together in the embedding space for a given inspection image. Evaluation results show that EmInspector can effectively mitigate backdoor attacks on FSSL across various adversary settings. Our code is avaliable at https://github.com/ShuchiWu/EmInspector.

cs.CR↗

arXiv2024

Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations

Conventional synchronous federated learning (SFL) frameworks suffer from performance degradation in heterogeneous systems due to imbalanced local data size and diverse computing power on the client side. To address this problem, asynchronous FL (AFL) and semi-asynchronous FL have been proposed to recover the performance loss by allowing asynchronous aggregation. However, asynchronous aggregation incurs a new problem of inconsistency between local updates and global updates. Motivated by the issues of conventional SFL and AFL, we first propose a time-driven SFL (T-SFL) framework for heterogeneous systems. The core idea of T-SFL is that the server aggregates the models from different clients, each with varying numbers of iterations, at regular time intervals. To evaluate the learning performance of T-SFL, we provide an upper bound on the global loss function. Further, we optimize the aggregation weights to minimize the developed upper bound. Then, we develop a discriminative model selection (DMS) algorithm that removes local models from clients whose number of iterations falls below a predetermined threshold. In particular, this algorithm ensures that each client's aggregation weight accurately reflects its true contribution to the global model update, thereby improving the efficiency and robustness of the system. To validate the effectiveness of T-SFL with the DMS algorithm, we conduct extensive experiments using several popular datasets including MNIST, Cifar-10, Fashion-MNIST, and SVHN. The experimental results demonstrate that T-SFL with the DMS algorithm can reduce the latency of conventional SFL by 50\%, while achieving an average 3\% improvement in learning accuracy over state-of-the-art AFL algorithms.

cs.LG↗