Communication Overhead Research Articles

PQSF: post-quantum secure privacy-preserving federated learning

In federated learning, secret sharing is a key technology to maintain the privacy of participants’ local models. Moreover, with the rapid development of quantum computers, existing federated learning privacy protection schemes based on secret sharing will no longer be able to guarantee the data security of participants in the post-quantum era. In addition, existing privacy protection methods have the problem of high communication and computational overhead. Although the multi-stage secret sharing scheme proposed by Pilaram et al. is one of the effective solutions to the above problems, existing studies have proven the privacy leakage risk of this scheme. This paper firstly designs a new lattice-based multi-stage secret sharing scheme Improved-Pilaram to solve the security problem, which allows participants to use public vectors to reconstruct different secret values without changing the secret sharing. Based on Improved-Pilaram, this article proposes a post-quantum secure federated learning scheme PQSF. PQSF uses double masking technology to encrypt model parameters and achieves mask reconstruction through secret sharing. Since Improved-Pilaram is multi-stage, participants do not need to update their local secret shares frequently during training. Analysis and experimental results show that the PQSF proposed in this paper reduces the communication complexity between participants and reduces the computational overhead by about 20% compared with existing solutions.

Adaptive event-triggered stochastic estimator-based sampled-data fuzzy control for fractional-order permanent magnet synchronous generator-based wind energy systems

This study aims to develop an adaptive event-triggered estimation sampled-data control method for a fractional-order permanent magnet synchronous generator (PMSG)-based wind energy system (WES) using the Takagi–Sugeno (T–S) fuzzy approach. Unlike existing PMSG-based WES control schemes, we propose an aperiodic event-triggered communication scheme with an adaptive mechanism to reduce data transmission. To address the challenge of limited communication resources, we introduce an adaptive event-triggered (AET) estimation method with aperiodic sampling, significantly reducing communication overhead while maintaining stable WES performance. This method employs transmission techniques based on absolute errors, resulting in high data transmission efficiency. First, the fractional-order model for the PMSG-based WES is represented using linear sub-models through the T–S fuzzy approach. Next, a fuzzy aperiodic AET mechanism is proposed for the PMSG model with augmented estimation error systems. Then, the fractional Lyapunov function theory is employed to derive linear matrix inequalities (LMIs), ensuring bounded mean-square stability for the PMSG-based WES with the augmented estimation error systems. Additionally, the desired estimator control gains are determined through solvable LMIs. Finally, simulation studies are presented to demonstrate the superiority and feasibility of the proposed control scheme.

Employing artificial intelligence to steer exascale workflows with colmena

Computational workflows are a common class of application on supercomputers, yet the loosely coupled and heterogeneous nature of workflows often fails to take full advantage of their capabilities. We created Colmena to leverage the massive parallelism of a supercomputer by using Artificial Intelligence (AI) to learn from and adapt a workflow as it executes. Colmena allows scientists to define how their application should respond to events (e.g., task completion) as a series of cooperative agents. In this paper, we describe the design of Colmena, the challenges we overcame while deploying applications on exascale systems, and the science workflows we have enhanced through interweaving AI. The scaling challenges we discuss include developing steering strategies that maximize node utilization, introducing data fabrics that reduce communication overhead of data-intensive tasks, and implementing workflow tasks that cache costly operations between invocations. These innovations coupled with a variety of application patterns accessible through our agent-based steering model have enabled science advances in chemistry, biophysics, and materials science using different types of AI. Our vision is that Colmena will spur creative solutions that harness AI across many domains of scientific computing.

Generalizing Random Butterfly Transforms to Arbitrary Matrix Sizes

Parker and Lê introduced random butterfly transforms (RBTs) as a preprocessing technique to replace pivoting in dense LU factorization. Unfortunately, their FFT-like recursive structure restricts the dimensions of the matrix. Furthermore, on multi-node systems, efficient management of the communication overheads restricts the matrix’s distribution even more. To remove these limitations, we have generalized the RBT to arbitrary matrix sizes by truncating the dimensions of each layer in the transform. We expanded Parker’s theoretical analysis to generalized RBT, specifically that in exact arithmetic, Gaussian elimination with no pivoting will succeed with probability 1 after transforming a matrix with full-depth RBTs. Furthermore, we experimentally show that these generalized transforms improve performance over Parker’s formulation by up to 62 % while retaining the ability to replace pivoting. This generalized RBT is available in the SLATE numerical software library.

Energy-efficient and location-aware IoT and WSN-based precision agricultural frameworks

Precision agriculture has emerged as a promising approach to enhance crop yield, reduce environmental impact, and optimize resource utilization through advanced sensing and automation technologies. This paper proposes an energy-efficient and location-aware framework for Internet of Things (IoT) and Wireless Sensor Networks (WSN)-based precision agriculture systems. The framework leverages low-power wireless communication protocols, adaptive sensor scheduling, and location-based clustering algorithms to minimize energy consumption and prolong the network lifetime. Key features include real-time monitoring of soil moisture, temperature, humidity, and crop health through geographically distributed sensors, with automated decision-making for irrigation, fertilization, and pest control. The proposed framework also integrates machine learning models for predictive analysis and anomaly detection, enabling early identification of potential issues that could adversely affect crop productivity. Simulation results demonstrate a significant reduction in energy consumption and communication overhead, while maintaining high accuracy in environmental parameter monitoring and resource allocation. This framework offers a scalable and robust solution for implementing sustainable precision agriculture practices, particularly in remote and resource-constrained areas

Efficient Maliciously Secure Oblivious Exponentiations

Oblivious Pseudorandom Functions (OPRFs) allow a client to evaluate a pseudorandom function (PRF) on her secret input based on a key that is held by a server. In the process, the client only learns the PRF output but not the key, while the server neither learns the input nor the output of the client. The arguably most popular OPRF is due to Naor, Pinkas and Reingold (Eurocrypt 2009). It is based on an Oblivious Exponentiation by the server, with passive security under the Decisional Diffie-Hellman assumption. In this work, we strengthen the security guarantees of the NPR OPRF by protecting it against active attacks of the server. We have implemented our solution and report on the performance. Our main result is a new batch OPRF protocol which is secure against maliciously corrupted servers, but is essentially as efficient as the semi-honest solution. More precisely, the computation (and communication) overhead is a multiplicative factor o ( 1 ) as the batch size increases. The obvious solution using zero-knowledge proofs would have a constant factor overhead at best, which can be too expensive for certain deployments. Our protocol relies on a novel version of the DDH problem, which we call the Oblivious Exponentiation Problem (OEP), and we give evidence for its hardness in the Generic Group model. We also present a variant of our maliciously secure protocol that does not rely on the OEP but nevertheless only has overhead o ( 1 ) over the known semi-honest protocol. Moreover, we show that our techniques can also be used to efficiently protect threshold blind BLS signing and threshold ElGamal decryption against malicious attackers.

Federated deep learning models for detecting RPL attacks on large-scale hybrid IoT networks

With the rapid spread of the Internet of Things (IoT), smart applications and services become increasingly crucial, making them an easily accessible source of personally identifiable information. Over the last few years, the use of machine learning in securing routing layers, particularly routing protocol for low-power and lossy networks (RPL), has become fundamental in ensuring successful routing and privacy preservation as a crucial consideration among edge nodes. In recent works, training of collected data on a central server has increased concerns regarding data privacy. Consequently, decentralized learning is currently a solution for privacy preservation. It has gained popularity in IoT networks in which the models are trained on hybrid data located in edge nodes and enable global decision-making without sharing global data, causing high communication costs during weight updates. We propose a federated learning of routing protocol (Fed-RPL)-based gated recurrent unit (GRU) model for decentralized training rounds and quantization method (Q-8bit) to decrease the number of weight updates that can significantly mitigate the communication overhead and maintain the local model with high accuracy. Meanwhile, the ensemble unit aggregates the updates and selects the best local model to enhance the global model accuracy. Our experiments show that Fed-RPL outperforms classical machine learning (ML) methods in privacy-preserving edge data, significantly reduces the communication cost in non-IID scenarios, and achieves higher detection accuracy than recent FL approaches.

Edge-device collaborative computing for multi-view classification

Motivated by the proliferation of Internet-of-Thing (IoT) devices and the rapid advances in the field of deep learning, there is a growing interest in pushing deep learning computations, conventionally handled by the cloud, to the edge of the network to deliver faster responses to end users, reduce bandwidth consumption to the cloud, and address privacy concerns. However, to fully realize deep learning at the edge, two main challenges still need to be addressed: (i) how to meet the high resource requirements of deep learning on resource-constrained devices, and (ii) how to leverage the availability of multiple streams of spatially correlated data, to increase the effectiveness of deep learning and improve application-level performance. To address the above challenges, we explore collaborative inference at the edge, in which edge nodes and end devices share correlated data and the inference computational burden by leveraging different ways to split computation and fuse data. Besides traditional centralized and distributed schemes for edge-end device collaborative inference, we introduce selective schemes that decrease bandwidth resource consumption by effectively reducing data redundancy. As a reference scenario, we focus on multi-view classification in a networked system in which sensing nodes can capture overlapping fields of view. The proposed schemes are compared in terms of accuracy, computational expenditure at the nodes, communication overhead, inference latency, robustness, and noise sensitivity. Experimental results highlight that selective collaborative schemes can achieve different trade-offs between the above performance metrics, with some of them bringing substantial communication savings (from 18% to 74% of the transmitted data with respect to centralized inference) while still keeping the inference accuracy well above 90%.

Enhancing the Vehicular Public Key Infrastructure to Develop Privacy-Preserving Authentication Scheme for Vanet by Using PCM and MSS Scheme

This article proposes a security-based authentication as well as efficient certificate management approach for VANET to detect fraudulent nodes with better precision, less latency and overhead. The primary purpose of the developed system is to establish effectual and heftiness of VANET security that lead to the stability of overall network. VANETs are composed of vehicles and Road Side Units (RSUs) assisting with network management and the vehicles connect with one another and RSUs to furnish roadside information and safety solutions. Security is an essential factor in VANETs because the confidentiality of humans (passengers) is paramount; hence, Vehicular Public Key Infrastructure (VPKI) is utilised to offer authentication and safety services in VANETs. The developed structure provides an encrypted VANET transmission infrastructure by utilising the concepts of Merkle Signature Scheme (MSS) and Pseudo-code Certificate Management (PCM) to minimise overhead for communication and latency while ensuring entity authenticity. Messages are authenticated by sender, encoded with a vehicular public key distributed by a PCM-MSS and decrypted by the destination, resulting in every transmission including a certification from a reliable authority. During that verification, the transmitter and receiver of message’s authentication and validation is accomplished. Simulation findings show that the proposed approach improves the reliability of identifying hostile nodes and PDR while reducing authentication delays and overhead.

Verifiable attribute-based multi-keyword search scheme with sensitive information hiding for cloud-assisted e-healthcare sharing systems

Cloud-assisted e-healthcare sharing systems (EHSSs) play an increasingly pivotal role in the contemporary healthcare field. By outsourcing electronic medical records (EMRs) to the cloud, hospitals can alleviate local storage and management burdens while facilitating data sharing. Due to the highly sensitive nature of EMRs, encryption is necessary before storing them on the cloud. Attribute-based keyword search (ABKS) enables the privacy protection of EMRs with efficient search services. However, there remain some limitations in practical application. Firstly, most ABKS schemes only support single keyword queries, resulting in inaccurate results and wastage of computing and bandwidth resources. Secondly, since sensitive information within EMRs is encrypted as a whole, different data users (including internal doctors and external researchers) should have varying access rights to prevent leakage of this sensitive information. Thirdly, incorrect search results could lead to misdiagnosis or endanger patients' lives and affect researchers' decision-making processes. To effectively tackle these challenges, this paper proposes a verifiable attribute-based multi-keyword search scheme with sensitive information hiding (VABMKS-SIH) for cloud-assisted EHSSs, where we present a secure model for multi-keyword search with two-level access structure by incorporating an improved blindness filtering technique into ciphertext-policy attribute-based encryption (CP-ABE) within existing keyword search framework. Our scheme employs a super-increasing sequence to aggregate multiple filtered data blocks into one unified ciphertext, thereby greatly reducing communication overhead during the transmission phases of ciphertext. To check the correctness of returned results, we introduce a lightweight algebraic signature algorithm based on fundamental algebraic operations. A security analysis demonstrates that VABMKS-SIH is provably secure under the random oracle mode. Additionally, we also evaluate the proposed scheme's performance to demonstrate its utility in cloud-assisted EHSSs.

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.

Research on distributed optimal scheduling method based on consensus

Abstract With access to large-scale distributed power sources, the physical structure of the power grid system tends to be distributed. The application of traditional centralized optimal scheduling methods will lead to a surge in communication overhead and computational complexity, which will affect the performance and efficiency of the solution. In this paper, the minimum operating cost of the system is taken as the goal, and the distributed direct current optimal power flow (DC-OPF) optimization calculation of the photovoltaic-storage power generation system is considered to approximately solve the economic dispatch problem. The DC optimal power flow model with energy storage charging penalty is constructed. Then, the distributed optimization method based on the consensus alternating direction multiplier method (ADMM) is adopted. By decoupling the objective function and constraints of the whole system problem, the fully distributed DC-OPF calculation is realized by introducing the global consensus variable to deal with the boundary buses. Finally, the improved IEEE 30-bus example is used to test the method, and the simulation results verify the convergence and accuracy of the method.

EPAKA: An efficient and privacy-preserving authenticated key agreement scheme based on physical security for VANET

Vehicular ad hoc network (VANET) has been a promising technology in smart transportation system, which can enable information exchange between vehicles and roadside units (RSUs). However, the privacy of vehicles and RSUs is a critical challenge in VANET, as they may expose sensitive information to malicious attackers or unauthorized parties. Many existing authenticated key agreement (AKA) schemes aim to protect the privacy of vehicles and RSUs, but they often neglect the physical security of the devices involved in the communication. Therefore, we propose an efficient and privacy-preserving AKA scheme in VANET, which embeds physical unclonable function (PUF) and fuzzy extraction (FE) technology. PUF is a physical device that generates random strings based on their intrinsic characteristics and external inputs, which can protect the secrets in the devices from being stolen by attackers. FE can compensate for the drawbacks of PUF affected by environmental factors. Our scheme preserves the identity privacy of legitimate RSUs and vehicles, as well as intercepts and traces the identity of malicious attackers. In addition, we eliminate the involvement of the third party (TP) in the AKA phase to better meet the high-speed driving of vehicles. Finally, we conduct formal and informal security analyses in random oracle model (ROM), which prove that our scheme can resist various attacks. We also show in the performance analysis that our scheme has the lowest computational cost, communication overhead, and total energy consumption.

OASR-WFBP: An overlapping aware start-up sharing gradient merging strategy for efficient communication in distributed deep learning

Wait-Free-Back-Propagation (WFBP) is a practical method for distributed deep-learning, but it suffers from a high communication overhead. To address this issue, the communication overhead can be reduced by overlapping gradient communication and computation, and sharing the startup time among multiple gradient communication phases. However, existing optimizations choose to share the startup time greedily and fail to coordinately exploit the overlapping opportunity between computation and communication. We propose an overlapping aware startup sharing Wait-Free-Back-Propagation (OASR-WFBP). An analytic model is designed to guide the sharing procedure. Evaluations show that OSAR-WFBP achieves a 5%-16% optimization in iteration time over the state-of-the-art WFBP algorithm.

FAM: Adaptive federated meta-learning for MRI data

Federated learning enables multiple clients to collaborate to train a model without sharing data. Clients with insufficient data or data diversity participate in federated learning to learn a model with superior performance. MRI data suffers from inadequate data and different data distribution due to differences in MRI scanners and client characteristics. Also, privacy concerns preclude data sharing. In this work, we propose a novel adaptive federated meta-learning (FAM) mechanism for collaboratively learning a single global model, which is personalized locally on individual clients. The learnt sparse global model captures the common features in the MRI data across clients. This model is grown on each client to learn a personalized model by capturing additional client-specific parameters from local data. Experimental results on multiple data sets show that the personalization process at each client quickly converges using a limited number of epochs. The personalized client models outperformed the locally trained models, demonstrating the efficacy of the FAM mechanism. Additionally, the FAM-based sparse global model has fewer parameters that require less communication overhead during federated learning. This makes the model viable for networks with limited resources.

Privacy-preserving and verifiable convolution neural network inference and training in cloud computing

With the rapid development of cloud computing, outsourcing massive data and complex deep learning model to cloud servers (CSs) has become a popular trend, which also brings some security problems. One is that the model stored in the CSs may be corrupted, leading to incorrect inference and training results. The other is that the privacy of outsourced data and model may be compromised. However, existing privacy-preserving and verifiable inference schemes suffer from low detection probability, high communication overhead and substantial computational time. To solve the above problems, we propose a privacy-preserving and verifiable scheme for convolutional neural network inference and training in cloud computing. In our scheme, the model owner generates the authenticators for model parameters before uploading the model to CSs. In the phase of model integrity verification, model owner and user can utilize these authenticators to check model integrity with high detection probability. Furthermore, we design a set of privacy-preserving protocols based on replicated secret sharing for both the inference and training phases, significantly reducing communication overhead and computational time. Through security analysis, we demonstrate that our scheme is secure. Experimental evaluations show that the proposed scheme outperforms existing schemes in privacy-preserving inference and model integrity verification.

SIGMA: Secure GPT Inference with Function Secret Sharing

Secure 2-party computation (2PC) enables secure inference that offers protection for both proprietary machine learning (ML) models and sensitive inputs to them. However, the existing secure inference solutions suffer from high latency and communication overheads, particularly for transformers. Function secret sharing (FSS) is a recent paradigm for obtaining efficient 2PC protocols with a preprocessing phase. We provide Sigma, the first end-to-end system for secure transformer inference based on FSS. By constructing new FSS-based protocols for complex machine learning functionalities, such as Softmax, GeLU and SiLU, and also accelerating their computation on GPUs, Sigma improves the latency of secure inference of transformers by 11 - 19x over the state-of-the-art that uses preprocessing and GPUs. We present the first secure inference of generative pre-trained transformer (GPT) models. In particular, Sigma executes Meta's Llama2 (available on HuggingFace) with 13 billion parameters in 44 seconds and GPT2 in 1.6 seconds

An Internet of Vehicles road traffic data sharing scheme based on signcryption and editable blockchain

Aiming at the problems of low real-time update efficiency of traffic data and privacy leakage of vehicle users in the Internet of Vehicles (IoV) data sharing, an IoV road traffic data sharing scheme based on signcryption and editable blockchain is proposed. Road-Side Unit (RSU) implements proxy signcryption for sharing data based on the authorization of the vehicle, ensuring the reliability of data and reducing the frequent interaction between vehicles and authorized map companies when sharing data. The editable blockchain is implemented by the chameleon hash function, and no new blocks need to be generated when updating data, thereby reducing the storage overhead caused by updating data. Combined with editable blockchain and fog computing server, the storage, sharing and update of traffic data are better realized. Security analysis shows that the proposed scheme satisfies the confidentiality, integrity, verifiability and unforgeability. Simulation results show that the proposed scheme has less communication overhead and computing overhead.

Self-triggered MPC with adaptive prediction horizon for nano-satellite attitude control system

Nano-satellites are essential tools for various applications, including scientific experiments, deep space exploration and astronomical observation. Achieving precise model predictions is crucial for their successful operation. To address the intricate constraints of nano-satellites and enhance control performance, the Model Predictive Control (MPC) algorithm is an effective solution. However, implementing an MPC-based attitude control system in actual engineering scenarios presents significant challenges, primarily due to the substantial computational burden, especially given the limited onboard computing resources of nano-satellites. In this paper, we introduce a modified adaptive self-triggered model predictive control (ST-MPC) algorithm designed to stabilize the attitude of nano-satellites, while simultaneously reducing communication and computational overhead compared to traditional MPC methods. The proposed self-triggered mechanism dynamically determines the next trigger time according to the system state. Moreover, we incorporate considerations for the efficiency of actuators to address the constraints imposed by the magnetic torque characteristics within the modified self-triggered mechanism. Additionally, a strategy for adaptive prediction horizon is proposed to balance computation load and control accuracy. The results of our simulations demonstrate the effectiveness of the modified ST-MPC algorithm in comparison to both traditional MPC and standard ST-MPC approaches. This algorithm may have the potential to significantly impact attitude control applications for nano-satellites.

Active learning for efficient data selection in radio‐signal‐based positioning via deep learning

AbstractThe problem of user equipment positioning based on radio signals is considered via deep learning. As in most supervised‐learning tasks, a critical aspect is the availability of a relevant dataset to train a model. However, in a cellular network, the data‐collection step may induce a high communication overhead. As a result, to reduce the required size of the dataset, it may be interesting to carefully choose the positions to be labelled and to be used in the training. Therefore, an active learning approach for efficient data collection is proposed. It is first shown that significant gains (both in terms of positioning accuracy and size of the required dataset) can be obtained for the considered positioning problem using a genie. This validates the interest of active learning for positioning. Then, a practical method is proposed to approximate this genie.