Communication Rounds Research Articles

Efficient Integration of Rate-Adaptive Reconciliation with Syndrome-Based Error Estimation and Subblock Confirmation for Quantum Key Distribution.

An effective post-processing algorithm is essential for achieving high rates of secret key generation in quantum key distribution. This work introduces an approach to quantum key distribution post-processing by integrating the three main steps into a unified procedure: syndrome-based error estimation, rate-adaptive reconciliation, and subblock confirmation. The proposed scheme employs low-density parity-check codes to estimate the quantum bit error rate using the syndrome information, and to optimize the channel coding rates based on the Slepian-Wolf coding scheme for the rate-adaptive method. Additionally, this scheme incorporates polynomial-based hash verification in the subblock confirmation process. The numerical results show that the syndrome-based estimation significantly enhances the accuracy and consistency of the estimated quantum bit error rate, enabling effective code rate optimization for rate-adaptive reconciliation. The unified approach, which integrates rate-adaptive reconciliation with syndrome-based estimation and subblock confirmation, exhibits superior efficiency, minimizes practical information leakage, reduces communication rounds, and guarantees convergence to the identical key. Furthermore, the simulations indicate that the secret key throughput of this approach achieves the theoretical limit in the context of a BB84 quantum key distribution system.

FedLGA: Toward System-Heterogeneity of Federated Learning via Local Gradient Approximation.

Federated learning (FL) is a decentralized machine learning architecture, which leverages a large number of remote devices to learn a joint model with distributed training data. However, the system-heterogeneity is one major challenge in an FL network to achieve robust distributed learning performance, which comes from two aspects: 1) device-heterogeneity due to the diverse computational capacity among devices and 2) data-heterogeneity due to the nonidentically distributed data across the network. Prior studies addressing the heterogeneous FL issue, for example, FedProx, lack formalization and it remains an open problem. This work first formalizes the system-heterogeneous FL problem and proposes a new algorithm, called federated local gradient approximation (FedLGA), to address this problem by bridging the divergence of local model updates via gradient approximation. To achieve this, FedLGA provides an alternated Hessian estimation method, which only requires extra linear complexity on the aggregator. Theoretically, we show that with a device-heterogeneous ratio ρ , FedLGA achieves convergence rates on non-i.i.d. distributed FL training data for the nonconvex optimization problems with O ([(1+ρ)/√{ENT}] + 1/T) and O ([(1+ρ)√E/√{TK}] + 1/T) for full and partial device participation, respectively, where E is the number of local learning epoch, T is the number of total communication round, N is the total device number, and K is the number of the selected device in one communication round under partially participation scheme. The results of comprehensive experiments on multiple datasets indicate that FedLGA can effectively address the system-heterogeneous problem and outperform current FL methods. Specifically, the performance against the CIFAR-10 dataset shows that, compared with FedAvg, FedLGA improves the model's best testing accuracy from 60.91% to 64.44%.

A Memory-Efficient Federated Kernel Support Vector Machine for Edge Devices.

A federated learning (FL) scheme (denoted as Fed-KSVM) is designed to train kernel support vector machines (SVMs) over multiple edge devices with low memory consumption. To decompose the training process of kernel SVM, each edge device first constructs high-dimensional random feature vectors of its local data, and then trains a local SVM model over the random feature vectors. To reduce the memory consumption on each edge device, the optimization problem of the local model is divided into several subproblems. Each subproblem only optimizes a subset of the model parameters over a block of random feature vectors with a low dimension. To achieve the same optimal solution to the original optimization problem, an incremental learning algorithm called block boosting is designed to solve these subproblems sequentially. After training of the local models, the central server constructs a global SVM model by averaging the model parameters of these local models. Fed-KSVM only increases the iterations of training the local SVM models to save the memory consumption, while the communication rounds between the edge devices and the central server are not affected. Theoretical analysis shows that the kernel SVM model trained by Fed-KSVM converges to the optimal model with a linear convergence rate. Because of such a fast convergence rate, Fed-KSVM reduces the communication cost during training by up to 99% compared with the centralized training method. The experimental results also show that Fed-KSVM reduces the memory consumption on the edge devices by nearly 90% while achieving the highest test accuracy, compared with the state-of-the-art schemes.

DFSat: Deep Federated Learning for Identifying Cyber Threats in IoT-based Satellite Networks

The integration of satellite systems with smart computing and networking technologies, such as the Internet of Things (IoT), has intensely augmented sophisticated cyberattacks against satellite environments. Resisting cyber threats to complex and large-scale satellite configurations has been enormously challenging, owing to the deficiency of high-quality samples of attack data collected from distributed satellite networks. This study proposes a novel federated learning-based deep learning framework for intrusion detection, named DFSat, to identify cyberattacks from IoT-integrated satellite networks. We develop a distributed deep learning-enabled attack detection method using a recurrent neural network. We then build a federated learning architecture which, utilizes several IoT-integrated satellite networks to preserve the privacy and security of DFSat's parameters throughout the learning process. Extensive experiments have been conducted using communication rounds on an IoT-based network dataset to validate the efficiency of DFSat. The results revealed that the proposed framework significantly distinguishes complex cyberattacks, outperforming recent state-of-the-art intrusion detection techniques, validating its usefulness as a viable deployment framework in IoT-integrated satellite networks.

Latency Minimization for Wireless Federated Learning With Heterogeneous Local Model Updates

In this paper, we study the latency minimization problem for a wireless federated learning (FL) system with heterogeneous computation capability, where different edge devices perform different numbers of local model updates in each communication round. We formulate a total latency minimization problem with probabilistic device selection, taking into account both the communication and computation latency in the whole FL procedure. However, it is highly challenging to optimally solve this problem due to the coupling issues of model convergence and latency minimization problem caused by the heterogeneity of local model updates. Through convergence analysis, we reveal that decoupling the resource allocation variables from the model convergence is essential to reduce the problem to a single-round latency minimization problem. To solve this simplified problem, we propose an alternating optimization scheme to jointly consider communication and computation resource allocation and mitigate the straggler effect. We prove that the resulting sub-problems, i.e., bandwidth and computation capacity allocation, are both convex and can be optimally solved in closed form, respectively. Simulation results show that compared with the baseline scheme that allocates the communication and computation resources equally across edge devices, the proposed scheme can achieve up to 47.04% single-round latency reduction.

Constant-Round Private Decision Tree Evaluation for Secret Shared Data

Decision tree evaluation is extensively used in machine learning to construct accurate classification models. Often in the cloud-assisted communication paradigm cloud servers execute remote evaluations of classification models using clients' data. In this setting, the need for private decision tree evaluation (PDTE) has emerged to guarantee no leakage of information for the client's input nor the service provider's trained model i.e., decision tree. In this paper, we propose a private decision tree evaluation protocol based on the three-party replicated secret sharing (RSS) scheme. This enables us to securely classify inputs without any leakage of the provided input or the trained decision tree model. Our protocol only requires constant rounds of communication among servers, which is useful in a network with longer delays.Ma et al. (NDSS 2021) presented a lightweight PDTE protocol with sublinear communication cost with linear round complexity in the size of the input data. This protocol works well in the low latency network such as LAN while its total execution time is unfavourably increased in the WAN setting. In contrast, Tsuchida et al. (ProvSec 2020) constructed a constant round PDTE protocol at the cost of communication complexity, which works well in the WAN setting. Although their construction still requires 25 rounds, it showed a possible direction on how to make constant round PDTE protocols. Ji et al. (IEEE Transactions on Dependable and Secure Computing) presented a simplified PDTE with constant rounds using the function secret sharing (FSS) at the cost of communication complexity. Our proposed protocol only requires five rounds among the employed three servers executing secret sharing schemes, which is comparable to previously proposed protocols that are based on garbled circuits and homomorphic encryption. To further demonstrate the efficiency of our protocol, we evaluated it using real-world classification datasets. The evaluation results indicate that our protocol provides better concrete performance in the WAN setting that has a large network delay.

Learning Critically: Selective Self-Distillation in Federated Learning on Non-IID Data

Federated learning (FL) enables multiple clients to collaboratively train a global model while keeping local data decentralized. Data heterogeneity (non-IID) across clients has imposed significant challenges to FL, which makes local models re-optimize towards their own local optima and forget the global knowledge, resulting in performance degradation and convergence slowdown. Many existing works have attempted to address the non-IID issue by adding an extra global-model-based regularizing item to the local training but without an adaption scheme, which is not efficient enough to achieve high performance with deep learning models. In this paper, we propose a Selective Self-Distillation method for Federated learning (FedSSD), which imposes adaptive constraints on the local updates by self-distilling the global model’s knowledge and selectively weighting it by evaluating the credibility at both the class and sample level. The convergence guarantee of FedSSD is theoretically analyzed and extensive experiments are conducted on three public benchmark datasets, which demonstrates that FedSSD achieves better generalization and robustness in fewer communication rounds, compared with other state-of-the-art FL methods.

DSFedCon: Dynamic Sparse Federated Contrastive Learning for Data-Driven Intelligent Systems.

Federated learning (FL) makes it possible for multiple clients to collaboratively train a machine-learning model through communicating models instead of data, reducing privacy risk. Thus, FL is more suitable for processing data security and privacy for intelligent systems and applications. Unfortunately, there are several challenges in FL, such as the low training accuracy for nonindependent and identically distributed (non-IID) data and the high cost of computation and communication. Considering these, we propose a novel FL framework named dynamic sparse federated contrastive learning (DSFedCon). DSFedCon combines FL with dynamic sparse (DSR) training of network pruning and contrastive learning to improve model performance and reduce computation costs and communication costs. We analyze DSFedCon from the perspective of accuracy, communication, and security, demonstrating it is communication-efficient and safe. To give a practical evaluation for non-IID data training, we perform experiments and comparisons on the MNIST, CIFAR-10, and CIFAR-100 datasets with different parameters of Dirichlet distribution. Results indicate that DSFedCon can get higher accuracy and better communication cost than other state-of-the-art methods in these two datasets. More precisely, we show that DSFedCon has a 4.67-time speedup of communication rounds in MNIST, a 7.5-time speedup of communication rounds in CIFAR-10, and an 18.33-time speedup of communication rounds in CIFAR-100 dataset while achieving the same training accuracy.

AMFL: Resource-Efficient Adaptive Metaverse-Based Federated Learning for the Human-Centric Augmented Reality Applications.

The emergence of 5G technology has enabled the development of Metaverse applications that provide users with immersive experiences through augmented reality (AR) devices, and the integration of federated learning (FL) with the Metaverse AR (MAR) systems can enable many edge intelligence services in 5G. However, the presence of nonindependent and identically distributed (Non-IID) data across all AR users' devices, coupled with limited edge communication resources, makes it challenging to achieve human-centric Metaverse-related applications such as target detection or image classification that combine virtual content with real-world. To address these challenges, we propose a novel adaptive resource-efficient Metaverse-based FL (AMFL) algorithm for AR applications that mitigates the negative effect of Non-IID data and reduces resource costs as well as improves the quality of experience (QoE). We first analyze the impact of wireless communication factors such as CPU frequency, bandwidth, and transmission power on FL training performance by a toy example in the MAR systems. Based on this analysis, furthermore, we establish a Non-IID degree, model accuracy, and resource consumption-related QoE maximization problem under given resource budgets, which is a stochastic optimization problem with strongly coupled variables, including bandwidth, CPU frequency, and transmission power. Guided by the theoretical analysis, to solve this issue, AMFL employs a deep reinforcement learning (DRL)-based method to adaptively allocate resources. Numerical results demonstrate that AMFL can significantly improve the QoE by up to 30.28 % , and reduce communication round and energy costs by up to 81.08 % and 72.20 % , respectively, even under the worst Non-IID case, compared to benchmarks.

Communication Efficient and Provable Federated Unlearning

We study federated unlearning, a novel problem to eliminate the impact of specific clients or data points on the global model learned via federated learning (FL). This problem is driven by the right to be forgotten and the privacy challenges in FL. We introduce a new framework for exact federated unlearning that meets two essential criteria: communication efficiency and exact unlearning provability. To our knowledge, this is the first work to tackle both aspects coherently. We start by giving a rigorous definition of exact federated unlearning, which guarantees that the unlearned model is statistically indistinguishable from the one trained without the deleted data. We then pinpoint the key property that enables fast exact federated unlearning: total variation (TV) stability, which measures the sensitivity of the model parameters to slight changes in the dataset. Leveraging this insight, we develop a TV-stable FL algorithm called FATS, which modifies the classical FedAvg algorithm for TV Stability and employs local SGD with periodic averaging to lower the communication round. We also design efficient unlearning algorithms for FATS under two settings: client-level and sample-level unlearning. We provide theoretical guarantees for our learning and unlearning algorithms, proving that they achieve exact federated unlearning with reasonable convergence rates for both the original and unlearned models. We empirically validate our framework on 6 benchmark datasets, and show its superiority over state-of-the-art methods in terms of accuracy, communication cost, computation cost, and unlearning efficacy.

A hybrid model for energy-efficient Green Internet of Things enabled intelligent transportation systems using federated learning

In the rapidly evolving Internet of Things domain, managing voluminous data streams while ensuring energy efficiency remains a cardinal challenge. Our research introduces a hybrid model designed specifically for an IoT system. This paper sheds light on our unique framework that emphasizes efficient communication and prioritizes energy conservation. The innovative model architecture is lightweight, fostering compatibility with resource-constrained devices and paving the way for personalized federated averaging during training. A crucial highlight of our methodology includes local training using lightweight optimization instead of traditional data transmission, reducing energy overheads considerably. Furthermore, we propose a novel approach for model aggregation using personalized energy-aware averaging. This process iteratively refines a global model by aggregating received updates, drastically reducing the data transfer compared to conventional methods. Lastly, we integrate an energy-aware updates management system, continually monitoring device energy metrics and making adaptive data transmission and model update decisions. The model ensures optimal participation in global updates by consistently monitoring devices’ energy metrics and setting adaptive thresholds. This study leverages the richly annotated Udacity Self-Driving Car Dataset provided by Roboflow to evaluate a novel federated learning model to optimize energy consumption for IoT systems. Our experiments simulate real-world collaborative learning scenarios using the TensorFlow Federated (TFF). Our focus on energy consumption evaluation revealed that our proposed model offers significant energy savings when analyzed based on data communication round time and individual node training duration. A comparative analysis between the proposed and traditional models uncovers substantial improvements in energy efficiency. In our experiments, the proposed approach demonstrated a commendable accuracy of 93.27%. Notably, the local communication time was streamlined to 1.21 s, while the global communication was efficiently clocked at 4.76 s. When compared to traditional methods, these results not only underscore the effectiveness and efficiency of our methodology in the context of IoT systems but also highlight its superior performance.

Driver Maneuver Interaction Identification with Anomaly-Aware Federated Learning on Heterogeneous Feature Representations

Driver maneuver interaction learning (DMIL) refers to the classification task with the goal of identifying different driver-vehicle maneuver interactions (e.g., left/right turns). Existing conventional studies largely focused on the centralized collection of sensor data from the drivers' smartphones (say, inertial measurement units or IMUs, like accelerometer and gyroscope). Such a centralized mechanism might be precluded by data regulatory constraints. Furthermore, how to enable an adaptive and accurate DMIL framework remains challenging due to (i) complexity in heterogeneous driver maneuver patterns, and (ii) impacts of anomalous driver maneuvers due to, for instance, aggressive driving styles and behaviors. To overcome the above challenges, we propose AF-DMIL, an Anomaly-aware Federated Driver Maneuver Interaction Learning system. We focus on the real-world IMU sensor datasets (e.g., collected by smartphones) for our pilot case study. In particular, we have designed three heterogeneous representations for AF-DMIL regarding spectral, time series, and statistical features that are derived from the IMU sensor readings. We have designed a novel heterogeneous representation attention network (HetRANet) based on spectral channel attention, temporal sequence attention, and statistical feature learning mechanisms, jointly capturing and identifying the complex patterns within driver maneuver behaviors. Furthermore, we have designed a densely-connected convolutional neural network in HetRANet to enable the complex feature extraction and enhance the computational efficiency of HetRANet. In addition, we have designed within AF-DMIL a novel anomaly-aware federated learning approach for decentralized DMIL in response to anomalous maneuver data. To ease extraction of the maneuver patterns and evaluation of their mutual differences, we have designed an embedding projection network that projects the high-dimensional driver maneuver features into low-dimensional space, and further derives the exemplars that represent the driver maneuver patterns for mutual comparison. Then, AF-DMIL further leverages the mutual differences of the exemplars to identify those that exhibit anomalous patterns and deviate from others, and mitigates their impacts upon the federated DMIL. We have conducted extensive driver data analytics and experimental studies on three real-world datasets (one is harvested on our own) to evaluate the prototype of AF-DMIL, demonstrating AF-DMIL's accuracy and effectiveness compared to the state-of-the-art DMIL baselines (on average by more than 13% improvement in terms of DMIL accuracy), as well as fewer communication rounds (on average 29.20% fewer than existing distributed learning mechanisms).

HeFUN: Homomorphic Encryption for Unconstrained Secure Neural Network Inference

Homomorphic encryption (HE) has emerged as a pivotal technology for secure neural network inference (SNNI), offering privacy-preserving computations on encrypted data. Despite active developments in this field, HE-based SNNI frameworks are impeded by three inherent limitations. Firstly, they cannot evaluate non-linear functions such as ReLU, the most widely adopted activation function in neural networks. Secondly, the permitted number of homomorphic operations on ciphertexts is bounded, consequently limiting the depth of neural networks that can be evaluated. Thirdly, the computational overhead associated with HE is prohibitively high, particularly for deep neural networks. In this paper, we introduce a novel paradigm designed to address the three limitations of HE-based SNNI. Our approach is an interactive approach that is solely based on HE, called iLHE. Utilizing the idea of iLHE, we present two protocols: ReLU, which facilitates the direct evaluation of the ReLU function on encrypted data, tackling the first limitation, and HeRefresh, which extends the feasible depth of neural network computations and mitigates the computational overhead, thereby addressing the second and third limitations. Based on HeReLU and HeRefresh protocols, we build a new framework for SNNI, named HeFUN. We prove that our protocols and the HeFUN framework are secure in the semi-honest security model. Empirical evaluations demonstrate that HeFUN surpasses current HE-based SNNI frameworks in multiple aspects, including security, accuracy, the number of communication rounds, and inference latency. Specifically, for a convolutional neural network with four layers on the MNIST dataset, HeFUN achieves 99.16% accuracy with an inference latency of 1.501 s, surpassing the popular HE-based framework CryptoNets proposed by Gilad-Bachrach, which achieves 98.52% accuracy with an inference latency of 3.479 s.

SHED: A Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing

There is a growing interest in the distributed optimization framework that goes under the name of Federated Learning (FL). In particular, much attention is being turned to FL scenarios where the network is strongly heterogeneous in terms of communication resources (e.g., bandwidth) and data distribution. In these cases, communication between local machines (agents) and the central server (Master) is a main consideration. In this work, we present SHED, an original communication-constrained Newton-type (NT) algorithm designed to accelerate FL in such scenarios. SHED is by design robust to non independent identically distributed (non i.i.d.) data distributions, handles heterogeneity of agents’ communication resources (CRs), only requires sporadic Hessian computations, and achieves global asymptotic super-linear convergence. This is possible thanks to an incremental strategy, based on eigendecomposition of the local Hessian matrices, which exploits (possibly) outdated second-order information. SHED is thoroughly validated on real datasets by assessing (i) the number of communication rounds required for convergence, (ii) the overall amount of data transmitted and (iii) the number of local Hessian computations. For all these metrics, SHED shows superior performance against state-of-the art techniques like BFGS, GIANT and FedNL.

Harnessing federated generative learning for green and sustainable Internet of Things

The rapid proliferation of devices in the Internet of Things (IoT) has ushered in a transformative era of data-driven connectivity across various domains. However, this exponential growth has raised pressing concerns about environmental sustainability and data privacy. In response to these challenges, this paper introduces One-shot Federated Learning (OSFL), an innovative paradigm that harmonizes sustainability and machine learning within IoT ecosystems. OSFL revolutionizes the traditional Federated Learning (FL) workflow by condensing multiple iterative communication rounds into a single operation, thus significantly reducing energy consumption, communication overhead, and latency. This breakthrough is coupled with the strategic integration of generative learning techniques, ensuring robust data privacy while promoting efficient knowledge sharing among IoT devices. By curtailing resource utilization, OSFL aligns seamlessly with the vision of green and sustainable IoT, effectively extending device lifespans and mitigating their environmental footprint. Our research underscores the transformative potential of OSFL, poised to reshape the landscape of IoT applications across domains such as energy-efficient smart cities and groundbreaking healthcare solutions. This contribution marks a pivotal step towards a more responsible, sustainable, and technologically advanced future.

Fragmentation of data packets in wireless sensor network with variable temperature and channel conditions

This study formalizes and solves the problem of minimizing the energy dissipated by a node in order to successfully transmit the initial data amount during one round of communication over a wireless channel affected by Rice fading under varying temperature conditions. In this work, the models for the temperature dependence of the parameters in an incoherent frequency shift key (FSK) demodulator are presented and investigated for the first time, taking into account both the frequency separation and the synchronization type of the clock generator. The studied orthogonality coefficients of FSK signals represent internal parameters in the proposed model of the incoherent Rice wireless channel. This model allows the analytical relationship between the bit error probability (BEP) and node heating temperature, signal fading depth in the channel (Rician K-factor), and signal-to-noise ratio (SNR) to be established.Since it is necessary to retransmit the entire data packet when an erroneous bit is detected in a communication system that uses an automatic repeat request, at high BEP values, it is recommended to fragment packets in order to improve the energy efficiency of the nodes. By using the developed models for calculating energy losses during the communication round, it was determined that optimal fragmentation options (OFO) for data packets can be identified within specific ranges of temperature and Rician K-factor, which includes the overhead costs for packeting and retransmission. As a result, OFO matrices of packets in the "temperature – K-factor" (t0–K) coordinate system were obtained for minimizing the energy loss of nodes at different SNR values. In our example of using TI CC2500 node transceivers for 90-day monitoring of corn vegetation, the t0K-Frag algorithm reduced node energy losses by a factor of K = 3.3 compared to the case of transmitting an unfragmented packet of initial length.

Sustainable and Round-Optimized Group Authenticated Key Exchange in Vehicle Communication

Vehicle authentication is an essential component validating the vehicle’s identity and ensuring the integrity of transformed data for intelligent transport vehicles (ITS) in the vehicular ad hoc network (VANET). Easy to deploy and operate privacy-enhancing vehicle authentication mechanisms are the mainstay for the widespread ITS in the VANET. Very recently, VANET security architectures are constituting by IEEE 1609.2 group, NoW project, the SeVeCom project. However, these approaches heavily depend on the consuming public key infrastructure (PKI) and certification authorities (CA). In this work, walking along the research line, we attempt to design authentication protocols with two diverse factors for Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) networks, respectively, without depending on the stumbling block PKI/CA. In addition, a smooth projective hash function (SPHF) (a.k.a., a special case of the designated-verifier zero-knowledge proof system) guarantees any recipient can confirm the authenticity and integrity of the received messages without knowing the authentication factors. Thus, to optimize the communication round, SPHF is used to design a (group) two-factor authenticated key exchange (AKE) with low-interactive communication rounds. The proof-of-concept implementation indicates that the computation and communication overheads introduced by our solution are acceptable in real-world deployments. The security of the proposed approach is validated using Bellare-Pointcheval-Rogaway (BPR) model along with the experimental evaluation and the theoretical analysis.

Single‐Photon Based Three‐Party Quantum Secure Direct Communication with Identity Authentication

AbstractMultipartite quantum secure direct communication (MQSDC) enables multiple message senders to simultaneously and independently transmit secret messages to a message receiver through quantum channels without sharing keys. Existing MQSDC protocols all assume that all the communication parties are legal, which is difficult to guarantee in practical applications. In this study, a single‐photon based three‐party QSDC protocol with identity authentication is proposed. In the protocol, the message receiver first authenticates the identity of two practical message senders. Only when the identity authentication is passed, the legal message senders can encode their messages by the hyper‐encoding technology. In theory, two bits of messages can be transmitted to the message receiver in a communication round. The protocol can resist the external attack and internal attack, and guarantee the security of the transmitted messages and the identity codes of each legal message sender. The secret message capacity of the protocol is simulated with two‐decoy‐state method. The maximal communication distance between any two communication parties can reach 31.75 km with weak signal and decoy state pulses. The three‐party QSDC protocol can be extended to a general MQSDC protocol and has important application in the further practical MQSDC field.

Enhancing security in Fiat–Shamir transformation-based non-interactive zero-knowledge protocols for IoT authentication

With the rapid expansion of IoT devices and their applications, there is an increasing demand for efficient and secure authentication mechanisms to protect against unauthorized access. Traditional authentication mechanisms face limitations regarding computational speed, communication costs, and vulnerability to cyber-attacks. Zero-knowledge proof (ZKP) protocols have emerged as an effective solution for achieving secure and efficient authentication in such environments without revealing sensitive information. Among ZKP protocols, Σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Sigma $$\\end{document}-protocols, a class of interactive ZKP protocols, have been employed for their efficiency and security. However, their interactive nature necessitates multiple rounds of communication, which can reduce efficiency and increase communication overhead for resource-constrained devices. Many works have aimed to eliminate the interaction of Σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Sigma $$\\end{document}-protocols by utilizing a transformation called the Fiat–Shamir transformation (FST). However, there is still a concern regarding the soundness of the FST as it can sometimes convert a secure Σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Sigma $$\\end{document}-protocol into an insecure non-interactive zero-knowledge (NIZK) authentication scheme. In this paper, we propose an approach for transforming Σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Sigma $$\\end{document}-protocols into a NIZK protocol based on the FST, yielding significant enhancements in efficiency, communication overhead reduction, and elimination of interaction. Our proposed protocol enables the completion of the authentication process in a single request while also strengthening the soundness of Σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Sigma $$\\end{document}-protocols in comparison with the traditional FST by requiring two authentication factors instead of one. To demonstrate our approach’s robustness, we conducted comprehensive informal and formal security analyses (using the Tamarin-Prover). Our protocol demonstrated completeness, soundness, zero-knowledge properties, and robustness against attacks, including eavesdropping, message modification, replay, and brute force attacks. Additionally, our performance analysis displayed a remarkable 50% improvement in computational cost compared to traditional Σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\Sigma $$\\end{document}-protocols, underscoring its efficiency for practical use.

PrivMaskFL: A private masking approach for heterogeneous federated learning in IoT

With the arrival of the era of the Internet of Things (IoT), the rapid development of new technologies such as artificial intelligence, big data, and other advanced techniques, data is growing geometrically. These data are prone to form data silos, scattered in various places. Jointly decentralized data applications will accelerate the progress and development of the times, but also face the challenge of data privacy protection. Federated learning (FL), a new branch of distributed machine learning, is trained by collaborative training to obtain global model without direct exposure to local datasets. Some studies have shown that typically federated learning involves a larger number of participants, it can lead to a significant increase in communication overhead, resulting in issues such as higher latency and bandwidth consumption. We suggest masking a subset of diverse participants and allowing the remaining participants to proceed with the next communication round of updates. Our aim is for reducing the communication overhead and improving the convergence performance of the global model on the premise of heterogeneous data privacy protection. We design a private masking approach PrivMaskFL to address two problems. We firstly propose a dynamic participant aggregation masking approach, which adopts the greedy ideology to select the relatively important participants and mask the unimportant ones; secondly, we design an adaptive differential privacy approach, which adaptively stratifies privacy budget according to the characteristics of participant, allocates the budget in a fine-grained stratified level, and adds Gaussian noise reasonably. Specifically, in each communication round, the participant’s model needs to perform local differential privacy noise addition for uplink parameter transmission; the server aggregates to acquire global model, finds a candidate participant subset based on the smaller parameter divergence by using the greedy algorithm approximation for t+1-th communication round for downlink parameter transmission. Subsequently, the privacy budget sequence is divided and granted to the participants of the stratified level, and the Gaussian noise addition of adaptive differential privacy is completed to achieve privacy protection without compromising the model’s usability. In experiments, our approach reduces the communication overhead and improve the convergence performance. Furthermore, our approach achieves higher accuracy and robust variance on both FMNIST and FEMNIST datasets.