Reduce Communication Cost Research Articles

A Privacy-Preserving System for Alzheimer's Disease Detection Based on Federated Learning

Alzheimer's disease is a severe neurodegenerative disorder that primarily affects the elderly. Early detection is crucial for enabling timely interventions and slowing the disease's progression. A promising approach for early detection involves analyzing audio data collected from elderly individuals in their homes using Internet of Things (IoT) devices. However, this method presents significant challenges concerning privacy and data security. This paper introduces EDP-AD (Efficient Differential Privacy-Alzheimer's Detection), an efficient and privacy-preserving system. The system utilizes small IoT devices to collect audio data from elderly individuals. By integrating machine learning, federated learning (FL) and differential privacy (DP) techniques, EDP-AD ensures that raw audio data remains local while breaking down data silos, thereby preventing potential privacy leaks during the disease detection process. To enhance system efficiency, a sparse mask updating algorithm based on Top-k is proposed. This algorithm reduces communication overhead by sparsifying the model parameters uploaded by clients within the FL framework. Evaluation on a real-world dataset shows that the system achieves an accuracy rate of 84.48%, reduces communication costs by two-thirds, and provides robust privacy protection while maintaining high efficiency.

CFNet:CSI compression feedback network based on WiFi sensing

Abstract To solve the problem of huge channel state information (CSI)data caused by a large number of antennas in large-scale MIMO systems,a CSI compressed feedback network model (CFNet)with encoder-decoder structure is proposed in this paper. Specifically, the encoder efficiently compresses the CSI data to reduce the burden of data transmission and storage. A key component, the Asymmetric Expansion Convolution (AEC) module, combines asymmetric convolution and dilated convolution to extract feature information from different directions, thereby increasing the model's receptive field and minimizing information loss. The compressed CSI is fed into a Gated Recurrent Unit (GRU), which captures long-term dependencies in the CSI sequence using the encoder's output and the hidden state of the upper window. Additionally, on the decoder side, the proposed Asymmetric Transpose Convolution reconstructs the compressed CSI data, enhancing the network's ability to capture and express CSI features through two complementary convolution operations, ultimately reducing communication costs. Thanks to the proposed encoder and decoder, CFNet can accurately identify fine-grained features of human activities recognition(HAR) while leveraging compressed sensing techniques, further improving data processing efficiency and recognition accuracy. The experiments conducted on two public datasets demonstrate that the evaluation metrics of the proposed network outperform those of advanced methods in the relevant field.

Efficient Distributed Sparse Relative Similarity Learning

Learning a good similarity measure for large-scale high-dimensional data is a crucial task in machine learning applications, yet it poses a significant challenge. Distributed minibatch stochastic gradient descent (SGD) serves as an efficient optimization method in large-scale distributed training, allowing linear speedup in proportion to the number of workers. However, communication efficiency in distributed SGD requires a sufficiently large minibatch size, presenting two distinct challenges. Firstly, a large minibatch size leads to high memory usage and computational complexity during parallel training of high-dimensional models. Second, a larger batch size of data reduces the convergence rate. To overcome these challenges, we propose an efficient distributed sparse relative similarity learning framework EDSRSL . This framework integrates two strategies: local minibatch SGD and sparse relative similarity learning. By effectively reducing the number of updates through synchronous delay while maintaining a large batch size, we address the issue of high computational cost. Additionally, we incorporate sparse model learning into the training process, significantly reducing computational cost. This paper also provides theoretical proof that the convergence rate does not decrease significantly with increasing batch size. Various experiments on six high-dimensional real-world datasets demonstrate the efficacy and efficiency of the proposed algorithms, with a communication cost reduction of up to \(90.89\%\) and a maximum wall time speedup of \(5.66\times\) compared to the baseline methods.

More Efficient Lattice-Based Electronic Voting from NTRU

In recent years, there has been much focus on developing core cryptographic primitives based on lattice assumptions, driven by the NIST call for post-quantum key encapsulation and digital signature algorithms. However, more work must be conducted on efficient privacy-preserving protocols based on quantum-safe assumptions. Electronic voting is one such privacy-preserving protocol whose adoption is increasing across the democratic world. E-voting offers both a fast and convenient alternative to postal voting whilst further ensuring cryptographic privacy of votes and offering full verifiability of the process. Owing to the sensitivity of voting and its infrastructure challenges, it is crucial to ensure security against quantum computers is baked into e-voting solutions. We present an e-voting scheme from quantum-safe assumptions based on the hardness of the RLWE and NTRU lattice problems, providing concrete parameters and an efficient implementation. Our design achieves a factor 5.3 × reduction in ciphertext size, 2.5 × reduction in total communication cost, and 2 × reduction in total computation time compared to the state-of-the-art lattice-based voting scheme by Aranha et al. (ACM CCS 2023). We argue that the efficiency of this scheme makes it suitable for real-world elections. Our scheme makes use of non-ternary NTRU secrets to achieve optimal parameters. In order to compute the security of our design, we extend the ternary-NTRU work of Ducas and van Woerden (ASIACRYPT 2021) by determining the concrete fatigue point (for general secrets) of NTRU to be q = 0.0058 · σ 2 · d 2.484 (above which parameters become overstretched) for modulus q , ring dimension d , and secrets drawn from a Gaussian of parameter σ . We consider this relation to be of independent interest and demonstrate its significance by improving the efficiency of the (partially) blind signature scheme by del Pino and Katsumata (CRYPTO 2022).

RAM-MEN: Robust authentication mechanism for IoT-enabled edge networks

The rapid expansion of Mobile Edge Computing (MEC) and the Internet of Things (IoT) has revolutionized technology by enabling real-time data processing at the network edge, which is essential for applications such as autonomous vehicles and smart cities. With the advent of 6G networks, which promise ultra-fast speeds, vast connectivity, and low-latency communication, MEC-IoT systems are becoming more powerful but also face significant security challenges. Existing authentication mechanisms (AMs) are often vulnerable to attacks like impersonation and insider threats. This paper introduces a novel lightweight AM, called RAM-MEN that employs cryptography and physically unclonable functions (PUFs) to secure IoT-enabled MEC environments in the 6G era. It protects against insider threats and fake MEC access points while ensuring efficiency and scalability. Additionally, the proposed RAM-MEN establishes a secure communication channel (session key) between IoT devices and the MEC server, enabling secure offloading of computationally intensive tasks. The security of the session is rigorously evaluated using formal methods, including Scyther and the random or real model, alongside informal approaches. Comparative performance evaluations show that the proposed RAM-MEN reduces communication costs by 21.54% to 45.53% and computational costs by 17.09% to 83.72%, while providing enhanced security features.

Towards practical and privacy-preserving CNN inference service for cloud-based medical imaging analysis: A homomorphic encryption-based approach.

Cloud-based Deep Learning as a Service (DLaaS) has transformed biomedicine by enabling healthcare systems to harness the power of deep learning for biomedical data analysis. However, privacy concerns emerge when sensitive user data must be transmitted to untrusted cloud servers. Existing privacy-preserving solutions are hindered by significant latency issues, stemming from the computational complexity of inner product operations in convolutional layers and the high communication costs of evaluating nonlinear activation functions. These limitations make current solutions impractical for real-world applications. In this paper, we address the challenges in mobile cloud-based medical imaging analysis, where users aim to classify private body-related radiological images using a Convolutional Neural Network (CNN) model hosted on a cloud server while ensuring data privacy for both parties. We propose PPCNN, a practical and privacy-preserving framework for CNN Inference. It introduces a novel mixed protocol that combines a low-expansion homomorphic encryption scheme with the noise-based masking method. Our framework is designed based on three key ideas: (1) optimizing computation costs by shifting unnecessary and expensive homomorphic multiplication operations to the offline phase, (2) introducing a coefficient-aware packing method to enable efficient homomorphic operations during the linear layer of the CNN, and (3) employing data masking techniques for nonlinear operations of the CNN to reduce communication costs. We implemented PPCNN and evaluated its performance on three real-world radiological image datasets. Experimental results show that PPCNN outperforms state-of-the-art methods in mobile cloud scenarios, achieving superior response times and lower usage costs. This study introduces an efficient and privacy-preserving framework for cloud-based medical imaging analysis, marking a significant step towards practical, secure, and trustworthy AI-driven healthcare solutions.

Analysis of OPC Data Using Federated Learning: An Evaluation of Performance and Privacy

This study examines the benefits of applying federated learning (FL) technology to OPC (Operational Performance Control) systems within industrial automation and data analysis processes. FL enables each production facility to process its data locally while only transmitting model parameters to a central server, thereby preserving data privacy. This approach provides significant advantages in industrial environments, particularly concerning data privacy and communication costs. The study evaluates FL's potential to ensure data privacy, reduce communication costs, improve efficiency in training time, and deliver high performance in predictive maintenance and quality estimation. Model performance was analyzed using accuracy, F1 score, precision, and loss metrics; the results demonstrated that FL achieved a 90% accuracy rate, offering competitive performance compared to centralized modeling. In predictive maintenance and quality analysis specifically, FL achieved 85-88% accuracy while reducing network data load by 65%. These findings validate that FL provides a secure, cost-effective, and efficient solution for industrial data analysis processes by eliminating the need for centralized data collection. In conclusion, FL and OPC integration supports data privacy, cost savings, and communication efficiency in industrial processes. The study highlights that FL could become a prevalent technology in industrial data analysis, establishing a new standard particularly in digital manufacturing processes.

A Lightweight ECC-Based Authentication and Key Agreement Protocol for IoT with Dynamic Authentication Credentials.

Due to the openness of communication channels and the sensitivity of the data being collected and transmitted, securing data access and communication in IoT systems requires robust ECC-based authentication and key agreement (AKA) protocols. However, designing an AKA protocol for IoT presents significant challenges, as most IoT sensors are deployed in resource-constrained, unattended environments with limited computational power, connectivity, and storage. To achieve anonymous authentication, existing solutions typically rely on shared temporary public keys to mask device IDs or validate sender certificates, which increases the computational overhead. Furthermore, these protocols often fail to address crucial security concerns, such as nonresistance to ephemeral secret leakage (ESL) attacks and a lack of perfect forward security. To mitigate the computational burden, we propose a dynamic authenticated credentials (DACs) synchronization framework for anonymous authentication. Then, we introduce an ECC-based AKA scheme that employs DACs in place of temporary public keys or sender credentials, enabling efficient and secure anonymous authentication. The security of the proposed protocol was rigorously verified under the Real-or-Oracle model and validated using ProVerif. Performance comparisons demonstrate that our scheme offered significant improvements in security, with an over 37% reduction in communication cost and computational overhead.

Minimizing Communication Overhead in Decentralized Deep Neural Networks

Minimizing communication overhead in decentralized deep neural network (DNN) training has become a critical challenge, particularly with the increasing adoption of distributed systems for large-scale machine learning tasks. This paper introduces advanced techniques that leverage gradient compression, adaptive sparsification, and hybrid aggregation to optimize communication efficiency while maintaining model accuracy and convergence rates. Experimental results on benchmark datasets such as CIFAR-10 and ImageNet show that the proposed methods reduce communication costs by up to 70% compared to standard approaches while achieving comparable or superior model accuracy. Additionally, scalability tests on diverse neural network architectures highlight the robustness of the approach, demonstrating efficient performance across varying network sizes and computational setups. These findings underscore the potential of the proposed strategies to enable faster, cost-effective, and sustainable decentralized deep learning systems.

Adaptive Client Clustering for Efficient Federated Learning Over Non-IID and Imbalanced Data

Federated learning (FL) is an emerging distributed and privacy-preserving machine learning framework. However, the performance of traditional FL methods is seriously impaired by the real-world data, which appear to be non-IID. The recent clustered federated learning (CFL) methods eliminate the impact of non-IID data by grouping clients with similar data distribution into the same cluster. Unfortunately, existing CFL methods heavily rely on the pre-setting of the cluster number, failing to achieve adaptive client clustering. We also experimentally observe that imbalanced data largely degrade their correctness of client clustering. In this paper, we present a novel CFL method without manual intervention, named AutoCFL, which can eliminate both effects of non-IID and imbalanced data simultaneously. To deal with imbalanced data, the local training adjustment strategy adaptively adjusts the number of local training epochs for each client. To further improve the clustering correctness and adaptability, the weighted voting-based client clustering strategy automatically groups each client into an appropriate cluster. Extensive experiments are conducted to evaluate the design of AutoCFL with three popular datasets under various data settings. Experimental results demonstrate that AutoCFL outperforms state-of-the-art methods, e.g., on average improving model accuracy by 9.24%, while reducing communication costs by 4.67 in an adaptive manner.

Federated Learning Client Pruning for Noisy Labels

Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy. However, existing FL methods often assume clean annotated datasets, impractical for resource-constrained edge devices. In reality, noisy labels are prevalent, posing significant challenges to FL performance. Prior approaches attempt label correction and robust training techniques but exhibit limited efficacy, particularly under high noise levels. This paper introduces ClipFL ( F ederated L earning Cli ent P runing), a novel framework addressing noisy labels from a fresh perspective. ClipFL identifies and excludes noisy clients based on their performance on a clean validation dataset, tracked using a Noise Candidacy Score (NCS). The framework comprises three phases: pre-client pruning to identify potential noisy clients and calculate their NCS, client pruning to exclude a percentage of clients with the highest NCS, and post-client pruning for fine-tuning the global model with standard FL on clean clients. Empirical evaluation demonstrates ClipFL’s efficacy across diverse datasets and noise levels, achieving accurate noisy client identification, superior performance, faster convergence, and reduced communication costs compared to state-of-the-art FL methods. Our code is available at https://github.com/MMorafah/ClipFL.

Distributed Decision‐Making of General Linear Systems in Multi‐Coalition Games and Its Application to USV Swarm Confrontation

ABSTRACTThis article explores a decision‐making problem with partial information in a multi‐coalition game that involves both cooperation and competition. Considering heterogeneous players with general linear systems, we propose a distributed algorithm that employs average consensus mechanisms to estimate the gradient of the coalition function among players within each coalition and utilizes leader‐following protocols to estimate the actions of all players across multiple coalitions. Furthermore, to reduce communication costs, a dynamic event‐triggered mechanism (ETM) is introduced into the average consensus and leader‐following protocols. The ETM is asynchronous, eliminating the requirement for a global clock and allowing players to transmit information only when the triggering condition is satisfied. By the Lyapunov analysis, all actions asymptotically converge to the Nash equilibrium by the proposed algorithms. Moreover, the unmanned surface vehicle (USV) swarm confrontation is formulated as a coalition game. In the scenario of safeguarding territorial integrity, we devise specific tasks for both the invading and defending USVs, encompassing elements such as formation, intrusion, defense, and so forth. The effectiveness of the proposed algorithms is validated through comprehensive simulations.

Privacy-preserving and communication-efficient stochastic alternating direction method of multipliers for federated learning

Federated learning constitutes a paradigm in distributed machine learning, wherein model training unfolds through the exchange of intermediary results between a central server and federated clients. Given its decentralized nature, conventional machine learning algorithms find limited applicability in the context of federated learning models. Hence, the alternating direction method of multipliers (ADMM), tailored for distributed optimization, is leveraged for this purpose. However, despite the considerable promise of the ADMM algorithm in federated learning, it faces challenges related to computational efficiency, communication efficiency, and data security. In response to these challenges, this study proposes the privacy-preserving and communication-efficient stochastic ADMM (PPCESADMM) algorithm that enhances the computational efficiency through the stochastic optimization method, reduces communication costs through sparse communication method, and ensures the security of federated clients' data via the homomorphic encryption method. Theoretical analyses confirm the convergence of the PPCESADMM algorithm under mild conditions and establish its convergence rate as O(1/T). Experiments illustrate the superior performance of our algorithm in communication cost compared to ADMM and CEADMM algorithms, achieving reductions of 65.10% and 44.32%, respectively. Furthermore, our method surpasses classical federated learning algorithms such as FedAvg, FedAvgM, and SCAFFOLD in terms of algorithmic convergence, achieving superior convergence precision within predefined training epochs. Finally, our algorithm converges to the same results as those obtained without using homomorphic encryption, albeit at the cost of increased computation time.

Ray decomposition radiation transport for high performance computing

Radiation transport is essential in many high-performance computing problems. However, its complexity presents computational challenges. This study presents a novel algorithm, the ray decomposition method for long characteristics transport, designed to address communication challenges specific to distributed memory computing. Reordering of ray property calculations reduces communication cost associated with sequential ray integration. Verification studies demonstrate solution convergence. Performance modeling of the ray decomposition method predicts the compute time from first principles. Consistency of experimentally measured performance with analytical predictions validates the performance scaling model. This work represents a step towards more scalable and efficient radiation transport simulations.

Does reducing communication barriers promote diversity?

We study how a reduction in communication cost affects equilibrium diversity (in expertise) in hiring decisions. The key trade-off is that, while hiring a more diverse team may enlarge the team's pool of knowledge, it also makes communication between the hired experts more challenging. Equilibrium diversity balances this trade-off. We find that equilibrium diversity may exhibit a U-shape relationship with communication cost, reaching its lowest point at moderate cost values, where experts' incentives to communicate are most sensitive to changes in diversity.

A Revocable Certificateless Encryption Scheme for Multi‐User

ABSTRACTCertificateless cryptography, which solves the key escrow problem and avoids the complexity of certificate management, is an important part of public key cryptography. In the multi‐user scenarios, broadcast encryption can improve computational efficiency and reduce communication cost. Moreover, there may be some malicious users in the above scenarios, and the decryption permissions of these users need an effective mechanism to revoke them. In this paper, a revocable certificateless encryption scheme for multi‐user (RCLE‐MU) is proposed to address this issue. In the scheme, the Cloud Server Provider (CSP) utilizes the master time key to periodically generate time keys for legitimate users. For illegitimate users, their decryption privileges are revoked since they are unable to obtain the time keys. Then this new scheme is proved to be ciphertext indistinguishable under selected identity and chosen‐ciphertext attacks (sID‐CCAs). Finally, compared with several other schemes, the new scheme has more efficiency advantage. So it is suitable for multi‐user scenarios.

RNEP: Random Node Entropy Pairing for Efficient Decentralized Training with Non-IID Local Data

The proliferation of edge devices and advancements in Internet of Things technology have created a vast array of distributed data sources, necessitating machine learning models that can operate closer to the point of data generation. Traditional centralized machine learning approaches often struggle with real-time big data applications, such as climate prediction and traffic simulation, owing to high communication costs. In this study, we introduce random node entropy pairing, a novel distributed learning method for artificial neural networks tailored to distributed computing environments. This method reduces communication overhead and addresses data imbalance by enabling nodes to exchange only the weights of their local models with randomly selected peers during each communication round, rather than sharing the entire dataset. Our findings indicate that this approach significantly reduces communication costs while maintaining accuracy, even when learning from non-IID local data. Furthermore, we explored additional learning strategies that enhance system accuracy by leveraging the characteristics of this method. The results demonstrate that random node entropy pairing is an effective and efficient solution for distributed learning in environments where communication costs and data distribution present significant challenges.

FLAV: Federated Learning for Autonomous Vehicle privacy protection

Autonomous Vehicle Systems are committed to safer, more efficient and more convenient transportation on the roads of the future. However, concerns about vehicle data privacy and security remain significant. Federated Learning, as a decentralized machine learning approach, allows multiple devices or data sources to collaboratively train models without sharing raw data, providing essential privacy protection. In this paper, we propose a privacy-preserving framework for autonomous vehicles, named FLAV. First, we use a multi-chain parallel aggregation strategy to transmit model parameters and design a model parameter filtering mechanism, which reduces communication overhead by filtering out the local model parameters of certain vehicles, thereby alleviating bandwidth pressure. Second, we introduce a dynamic adjustment mechanism that automatically adjusts regularization strength by comparing each vehicle’s local parameters with the cumulative parameters of preceding vehicles in the chain. This mechanism balances local training with global consistency, ensuring the model’s adaptability to local data while improving coordination between vehicles in the chain. Experimental results demonstrate that our proposed method reduces communication costs while improving model accuracy and privacy protection level, effectively ensuring the security of autonomous driving data.

RFCSC: Communication efficient reinforcement federated learning with dynamic client selection and adaptive gradient compression

In the field of public safety, high-quality data is often owned by governments, companies, and organizations, making it difficult to train effective models through centralized datasets. This paper leverages federated learning as a mechanism to address data privacy concerns. Within the federated learning framework, the data across different clients is typically Non-IID (non-Independently and Identically Distributed). Furthermore, The complexity of sensitive image recognition tasks in public safety, along with the large number of model parameters, can lead to communication congestion issues in federated learning. To solve these challenges, this paper proposes a Reinforcement Federated Client Selection and Gradient Compression Method(RFCSC). By integrating client data prototypes with accuracy metrics, we dynamically assess the contribution of each client in federated learning. Through an intelligent dynamic incentive mechanism based on reinforcement learning, high-quality client nodes are dynamically selected to participate in federated learning, achieving dynamic adaptive aggregation, reducing the influence of Non-IID data, reducing communication cost, enhancing model accuracy, and achieving a balance between quality and efficiency. To address the issue of high communication cost for parameter transmission, we propose an adaptive model compression strategy in reinforcement federated learning which make local clients find an appropriate compression rate. This approach not only reduces gradient communication overhead but also minimizes the impact of compression on model accuracy. The effectiveness of our proposed approach are corroborated through comprehensive experiments conducted on one private dataset and two public datasets.

Event-Triggered Model-Free Adaptive Control for Nonlinear Multiagent Systems Under Jamming Attacks.

This article addresses the security problem of tracking control for nonlinear multiagent systems against jamming attacks. It is assumed that the communication networks among agents are unreliable due to the existence of jamming attacks, and a Stackelberg game is introduced to depict the interaction process between multiagent systems and malicious jammer. First, the dynamic linearization model of the system is established by applying a pseudo-partial derivative method. Then, a novel model-free security adaptive control strategy is proposed, so that the multiagent systems can achieve bounded tracking control in the mathematical expectation sense in spite of jamming attacks. Furthermore, a fixed threshold event-triggered scheme is utilized to reduce communication cost. It is worth noting that the proposed methods only require the input and output information of the agents. Finally, the validity of the proposed methods is illustrated through two simulation examples.