Federated learning (FL) is vulnerable to backdoor attacks, where adversaries alter model behavior on target classification labels by embedding triggers into data samples. While these attacks have received considerable attention in horizontal FL, they are less understood for vertical FL (VFL), devices hold different features of the samples, and only server holds labels. In this work, we propose a novel attack VFL which (i) does not rely gradient information from (ii) considers potential...

Over-the-air computation (AirComp) is a disruptive technique for fast wireless data aggregation in Internet of Things (IoT) networks via exploiting the waveform superposition property multiple-access channels. However, performance AirComp bottlenecked by worst channel condition among all links between IoT devices and access point. In this paper, reconfigurable intelligent surface (RIS) assisted system proposed to boost received signal power thus mitigate bottleneck reconfiguring propagation...

Federated learning (FL), as an emerging edge artificial intelligence paradigm, enables many devices to collaboratively train a global model without sharing their private data. To enhance the training efficiency of FL, various algorithms have been proposed, ranging from first-order second-order methods. However, these cannot be applied in scenarios where gradient information is not available, e.g., federated black-box attack and hyperparameter tuning. address this issue, paper we propose...

Fine-tuning large language models (LLMs) on devices is attracting increasing interest. Recent works have fused low-rank adaptation (LoRA) techniques with federated fine-tuning to mitigate challenges associated device model sizes and data scarcity. Still, the heterogeneity of computational resources remains a critical bottleneck: while higher-rank modules generally enhance performance, varying capabilities constrain LoRA's feasible rank range. Existing approaches attempting resolve this issue...

Over-the-air computation (AirComp) is a promising technology that capable of achieving fast data aggregation in Internet Things (IoT) networks. The mean-squared error (MSE) performance AirComp bottlenecked by the unfavorable channel conditions. This limitation can be mitigated deploying reconfigurable intelligent surface (RIS), which reconfigures propagation environment to facilitate receiving power equalization. achievable RIS relies on availability accurate state information (CSI), however...

Intelligent reflecting surface (IRS) has the potential to significantly enhance network performance by reconfiguring wireless propagation environments. It is however difficult obtain accurate downlink channel state information (CSI) for efficient beamforming design in IRS-aided networks. In this article, we consider an multiple-input single-output (MISO) network, where base station (BS) not required know underlying distribution. We formulate outage probability minimization problem jointly...

In this paper, we consider fast wireless data aggregation via over-the-air computation (AirComp) in Internet of Things (IoT) networks, where an access point (AP) with multiple antennas aim to recover the arithmetic mean sensory from IoT devices. To minimize estimation distortion, formulate a mean-squared-error (MSE) minimization problem that involves joint optimization transmit scalars at devices as well denoising factor and receive beamforming vector AP. end, derive closed-form, resulting...

Devices located in remote regions often lack coverage from well-developed terrestrial communication infrastructure. This not only prevents them experiencing high quality services but also hinders the delivery of machine learning regions. In this paper, we propose a new federated (FL) methodology tailored to space-air-ground integrated networks (SAGINs) tackle issue. Our approach strategically leverages nodes within space and air layers as both (i) edge computing units (ii) model aggregators...

While traditional federated learning (FL) typically focuses on a star topology where clients are directly connected to central server, real-world distributed systems often exhibit hierarchical architectures. Hierarchical FL (HFL) has emerged as promising solution bridge this gap, leveraging aggregation points at multiple levels of the system. However, existing algorithms for HFL encounter challenges in dealing with multi-timescale model drift, i.e., drift occurring across data heterogeneity....

Over-the-air computation (AirComp) is a disruptive technique for fast wireless data aggregation in Internet of Things (IoT) networks via exploiting the waveform superposition property multiple-access channels. However, performance AirComp bottlenecked by worst channel condition among all links between IoT devices and access point. In this paper, reconfigurable intelligent surface (RIS) assisted system proposed to boost received signal power thus mitigate bottleneck reconfiguring propagation...

This letter proposes a novel scheme of joint antenna combination and symbol detection in multi-input multi-output (MIMO) systems, which simultaneously determines the coefficients to lower RF chains designs minimum bit error rate (MBER) detector mitigate interference. The decision statistic, however, is highly nonlinear particle swarm optimization (PSO) algorithm employed reduce computational overhead. Simulations show that new approach yields satisfactory performance with reduced overhead...

Intelligent reflecting surface (IRS) has the potential to significantly enhance network performance by reconfiguring wireless propagation environments. It is however difficult obtain accurate downlink channel state information (CSI) for efficient beamforming design in IRS-aided networks. In this article, we consider an multiple-input single-output (MISO) network, where base station (BS) not required know underlying distribution. We formulate outage probability minimization problem jointly...

Over-the-air computation (AirComp) is a promising technology that capable of achieving fast data aggregation in Internet Things (IoT) networks. The mean-squared error (MSE) performance AirComp bottlenecked by the unfavorable channel conditions. This limitation can be mitigated deploying reconfigurable intelligent surface (RIS), which reconfigures propagation environment to facilitate receiving power equalization. achievable RIS relies on availability accurate state information (CSI), however...

This paper presents a linear constrained minimum variance multiuser detection (MUD) scheme for DS-CDMA systems, which makes full use of the available spreading sequences users as well relevant channel information incoming rays in construction constraint matrix. To further enhance performance, statistical optimum filter bank combination with developed MUD partitioned interference canceller (PLIC) underlying structure is also addressed. The determination coefficients, however, calls...

Hierarchical federated learning (HFL) has demonstrated promising scalability advantages over the traditional "star-topology" architecture-based (FL). However, HFL still imposes significant computation, communication, and storage burdens on edge, especially when training a large-scale model resource-constrained Internet of Things (IoT) devices. In this paper, we propose hierarchical independent submodel (HIST), new FL methodology that aims to address these issues in settings. The key idea...

A simple, yet effective geometric method is presented to construct the signature sequences for multicarrier code-division multiple access (MC-CDMA) systems. By minimizing correlation of vectors, are recursively determined via projection onto a properly constructed subspace. Conducted simulations verify effectiveness method.

This paper addresses a simple, and yet effective approach to the design of block adaptive beamformers via parallel projection method (PPM), which is an extension classic onto convex set (POCS) inconsistent sets scenarios. The proposed begins with construction constraint weight vector beamformer lies in. are judiciously chosen force weights possess some desirable properties or meet prescribed rules. Based on minimum variance criterion fixed gain at look direction, two including considered....

Federated learning (FL), as an emerging edge artificial intelligence paradigm, enables many devices to collaboratively train a global model without sharing their private data. To enhance the training efficiency of FL, various algorithms have been proposed, ranging from first-order second-order methods. However, these cannot be applied in scenarios where gradient information is not available, e.g., federated black-box attack and hyperparameter tuning. address this issue, paper we propose...

In this paper, we consider fast wireless data aggregation via over-the-air computation (AirComp) in Internet of Things (IoT) networks, where an access point (AP) with multiple antennas aim to recover the arithmetic mean sensory from IoT devices. To minimize estimation distortion, formulate a mean-squared-error (MSE) minimization problem that involves joint optimization transmit scalars at devices as well denoising factor and receive beamforming vector AP. end, derive closed-form, resulting...