A game-theoretic approach for federated learning:A trade-off among privacy,accuracy and energy

Benefiting from the development of Federated Learning(FL)and distributed communication systems,large-scale intelligent applications become possible.Distributed devices not only provide adequate training data,but also cause privacy leakage and energy consumption.How to optimize the energy consumption in distributed communication systems,while ensuring the privacy of users and model accuracy,has become an urgent challenge.In this paper,we define the FL as a 3-layer architecture including users,agents and server.In order to find a balance among model training accuracy,privacy-preserving effect,and energy consumption,we design the training process of FL as game models.We use an extensive game tree to analyze the key elements that influence the players’decisions in the single game,and then find the incentive mechanism that meet the social norms through the repeated game.The experimental results show that the Nash equilibrium we obtained satisfies the laws of reality,and the proposed incentive mechanism can also promote users to submit high-quality data in FL.Following the multiple rounds of play,the incentive mechanism can help all players find the optimal strategies for energy,privacy,and accuracy of FL in distributed communication systems.

New pharmacological tools:the use of diterpenes to promote adult hippocampal neurogenesis

Tissue regeneration maintains homeostasis and preserves the functional features of each tissue.However,not all tissues show a strong repairing capacity.This is the case of the central nervous system.It is now well established that the generation of new functional neurons from stem cells in the adult brain occurs in specific regions of the brain of different species such as rodents,birds,primates,and humans(Eriksson et al.,1998).

Abnormal uterine bleeding successfully treated via ultrasoundguided microwave ablation of uterine myoma lesions: Three case reports

BACKGROUND Microwave endometrial ablation(MEA)is a minimally invasive treatment method for heavy menstrual bleeding.However,additional treatment is often required after recurrence of uterine myomas treated with MEA.Additionally,because this treatment ablates the endometrium,it is not indicated for patients planning to become pregnant.To overcome these issues,we devised a method for ultrasound-guided microwave ablation of uterine myoma feeder vessels.We report three patients successfully treated for heavy menstrual bleeding,secondary to uterine myoma,using our novel method.CASE SUMMARY All patients had a favorable postoperative course,were discharged within 4 h,and experienced no complications.Further,no postoperative recurrence of heavy menstrual bleeding was noted.Our method also reduced the myoma’s maximum diameter.CONCLUSION This method does not ablate the endometrium,suggesting its potential appli-cation in patients planning to become pregnant.

Glucagon-like peptide-1 receptor agonists as a possible intervention to delay the onset of type 1 diabetes:A new horizon

Type 1 diabetes(T1D)is a chronic autoimmune condition that destroys insulinproducing beta cells in the pancreas,leading to insulin deficiency and hyperglycemia.The management of T1D primarily focuses on exogenous insulin replacement to control blood glucose levels.However,this approach does not address the underlying autoimmune process or prevent the progressive loss of beta cells.Recent research has explored the potential of glucagon-like peptide-1 receptor agonists(GLP-1RAs)as a novel intervention to modify the disease course and delay the onset of T1D.GLP-1RAs are medications initially developed for treating type 2 diabetes.They exert their effects by enhancing glucose-dependent insulin secretion,suppressing glucagon secretion,and slowing gastric emptying.Emerging evidence suggests that GLP-1RAs may also benefit the treatment of newly diagnosed patients with T1D.This article aims to highlight the potential of GLP-1RAs as an intervention to delay the onset of T1D,possibly through their potential immunomodulatory and anti-inflammatory effects and preservation of beta-cells.This article aims to explore the potential of shifting the paradigm of T1D management from reactive insulin replacement to proactive disease modification,which should open new avenues for preventing and treating T1D,improving the quality of life and long-term outcomes for individuals at risk of T1D.

A Holistic Secure Communication Mechanism Using a Multilayered Cryptographic Protocol to Enhanced Security

In an era characterized by digital pervasiveness and rapidly expanding datasets,ensuring the integrity and reliability of information is paramount.As cyber threats evolve in complexity,traditional cryptographic methods face increasingly sophisticated challenges.This article initiates an exploration into these challenges,focusing on key exchanges(encompassing their variety and subtleties),scalability,and the time metrics associated with various cryptographic processes.We propose a novel cryptographic approach underpinned by theoretical frameworks and practical engineering.Central to this approach is a thorough analysis of the interplay between Confidentiality and Integrity,foundational pillars of information security.Our method employs a phased strategy,beginning with a detailed examination of traditional cryptographic processes,including Elliptic Curve Diffie-Hellman(ECDH)key exchanges.We also delve into encrypt/decrypt paradigms,signature generation modes,and the hashes used for Message Authentication Codes(MACs).Each process is rigorously evaluated for performance and reliability.To gain a comprehensive understanding,a meticulously designed simulation was conducted,revealing the strengths and potential improvement areas of various techniques.Notably,our cryptographic protocol achieved a confidentiality metric of 9.13 in comprehensive simulation runs,marking a significant advancement over existing methods.Furthermore,with integrity metrics at 9.35,the protocol’s resilience is further affirmed.These metrics,derived from stringent testing,underscore the protocol’s efficacy in enhancing data security.

Neural membrane repair at the core of regeneration

Loss of plasma membrane integrity can compromise cell functioning and viability.To countera ct this eminent threat,euka ryotic cells have developed efficient repair mechanisms,which seem to have co-evolved with the emergence of vital membrane processes(Cooper and McNeil,2015).This relationship between basic cellular functioning and membrane repair highlights the fundamental significance of preserving membrane integrity for cellular life.

Establishment of microneurovascular units in alginate hydrogel microspheres to reveal the anti-hypoxic effect of salidroside

Microneurovascular units(mNVUs),comprising neurons,micro-glia,and blood-brain barrier(BBB)endothelial cells,are pivotal to the central nervous system and are associated with cerebral hypoxia and brain injuries.Cerebral hypoxia triggers microglial overactivity,causing inflammation,neuronal injury,and disruption of the BBB[1].Salidroside(Sal),a key compound in Tibetan medicine Rhodiola crenulata,mitigates hypoxia-induced metabolic disorders and neuronal damage by preserving mitochondrial function[2].

Blockchain-Enabled Privacy Protection and Access Control Scheme Towards Sensitive Digital Assets Management

With the growth of requirements for data sharing,a novel business model of digital assets trading has emerged that allows data owners to sell their data for monetary gain.In the distributed ledger of blockchain,however,the privacy of stakeholder's identity and the confidentiality of data content are threatened.Therefore,we proposed a blockchainenabled privacy-preserving and access control scheme to address the above problems.First,the multi-channel mechanism is introduced to provide the privacy protection of distributed ledger inside the channel and achieve coarse-grained access control to digital assets.Then,we use multi-authority attribute-based encryption(MAABE)algorithm to build a fine-grained access control model for data trading in a single channel and describe its instantiation in detail.Security analysis shows that the scheme has IND-CPA secure and can provide privacy protection and collusion resistance.Compared with other schemes,our solution has better performance in privacy protection and access control.The evaluation results demonstrate its effectiveness and practicability.

SDGNN: Symmetry-Preserving Dual-Stream Graph Neural Networks

Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) are influential instruments for representation learning to a UWG, they invariably adopt a unique node feature matrix for illustrating the sole node set of a UWG.

2P3FL:A Novel Approach for Privacy Preserving in Financial Sectors Using Flower Federated Learning

The increasing data pool in finance sectors forces machine learning(ML)to step into new complications.Banking data has significant financial implications and is confidential.Combining users data from several organizations for various banking services may result in various intrusions and privacy leakages.As a result,this study employs federated learning(FL)using a flower paradigm to preserve each organization’s privacy while collaborating to build a robust shared global model.However,diverse data distributions in the collaborative training process might result in inadequate model learning and a lack of privacy.To address this issue,the present paper proposes the imple-mentation of Federated Averaging(FedAvg)and Federated Proximal(FedProx)methods in the flower framework,which take advantage of the data locality while training and guaranteeing global convergence.Resultantly improves the privacy of the local models.This analysis used the credit card and Canadian Institute for Cybersecurity Intrusion Detection Evaluation(CICIDS)datasets.Precision,recall,and accuracy as performance indicators to show the efficacy of the proposed strategy using FedAvg and FedProx.The experimental findings suggest that the proposed approach helps to safely use banking data from diverse sources to enhance customer banking services by obtaining accuracy of 99.55%and 83.72%for FedAvg and 99.57%,and 84.63%for FedProx.

Privacy-Preserving Consensus-Based Distributed Economic Dispatch of Smart Grids via State Decomposition

This paper studies the privacy-preserving distributed economic dispatch(DED)problem of smart grids.An autonomous consensus-based algorithm is developed via local data exchange with neighboring nodes,which covers both the islanded mode and the grid-connected mode of smart grids.To prevent power-sensitive information from being disclosed,a privacy-preserving mechanism is integrated into the proposed DED algorithm by randomly decomposing the state into two parts,where only partial data is transmitted.Our objective is to develop a privacy-preserving DED algorithm to achieve optimal power dispatch with the lowest generation cost under physical constraints while preventing sensitive information from being eavesdropped.To this end,a comprehensive analysis framework is established to ensure that the proposed algorithm can converge to the optimal solution of the concerned optimization problem by means of the consensus theory and the eigenvalue perturbation approach.In particular,the proposed autonomous algorithm can achieve a smooth transition between the islanded mode and the grid-connected mode.Furthermore,rigorous analysis is given to show privacy-preserving performance against internal and external eavesdroppers.Finally,case studies illustrate the feasibility and validity of the developed algorithm.

Statistical Process Monitoring Based on Ensemble Structure Analysis

Dear Editor,This letter presents a novel process monitoring model based on ensemble structure analysis(ESA).The ESA model takes advantage of principal component analysis(PCA),locality preserving projections(LPP),and multi-manifold projections(MMP)models,and then combines the multiple solutions within an ensemble result through Bayesian inference.In the developed ESA model,different structure features of the given dataset are taken into account simultaneously,the suitability and reliability of the ESA-based monitoring model are then illustrated through comparison.Introduction:The requirement for ensuring safe operation and improving process efficiency has led to increased research activity in the field of process monitoring.

Phosphodiesterase 9 localization in cytoplasm and nucleus:the gateway to selective targeting in neuroprotection?

The umbrella term"neurodege ne rative disorders"(NDDs) refers to several conditions characterized by a progressive loss of structure and function of cells belonging to the nervous system.Such diseases affect more than 50million people worldwide.Neurodegenerative disorders are characterized by sundry factors and pathophysiological mechanisms that a re challenging to be fully profiled.Many of these rely on cell signaling pathways to preserve homeostasis,involving second messengers such as cyclic adenosine monophosphate (cAMP)and cyclic guanosine 3',5'-monophosphate(cGMP).Their ability to control the duration and amplitude of the signaling cascade is given by the presence of several common and uncommon effectors.Protein kinases A and G (PKA and PKG),phosphodiesterases (PDEs),and scaffold proteins are among them.

Feature Matching via Topology-Aware Graph Interaction Model

Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers.This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model,is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous localitybased method without noticeable deterioration in processing time,adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching(TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.

Apatite Fission Track Thermochronology of Granite from the Xiazhuang Uranium Ore Field,South China:Implications for Exhumation History and Ore Preservation

Xiazhuang uranium ore field,located in the southern part of the Nanling Metallogenic Belt,is considered one of the largest granite-related U regions in South China.In this paper,we contribute new apatite fission track data and thermal history modeling to constrain the exhumation history and evaluate preservation potential of the Xiazhuang Uranium ore field.Nine Triassic outcrop granite samples collected from different locations of Xiazhuang Uranium ore field yield AFT ages ranging from 43 to 24 Ma with similar mean confined fission track lengths ranging from 11.8±2.0 to 12.9±1.9μm and Dpar values between 1.01 and 1.51μm.The robustness time-temperature reconstructions of samples from the hanging wall of Huangpi fault show that the Xiazhuang Uranium ore field experienced a time of monotonous and slow cooling starting from middle Paleocene to middle Miocene(~60-10 Ma),followed by relatively rapid exhumation in the late Miocene(~10-5 Ma)and nearly thermal stability in the Pliocene-Quaternary(~5-0 Ma).The amount of exhumation after U mineralization since the Middle Paleogene was estimated as~4.3±1.8 km according to the integrated thermal history model.Previous studies indicate that the ore-forming ages of U deposits in the Xiazhuang ore field are mainly before Middle Paleocene and the mineralization depths are more than 4.4±1.2 km.Therefore,the exhumation history since middle Paleocene plays important roles in the preservation of the Xiazhuang Uranium ore field.

Influence of tectonic preservation conditions on the nanopore structure of shale reservoir:A case study of Wufeng-Longmaxi Formation shale in western Hubei area,south China

Tectonism is one of the dominant factors affecting the shale pore structure.However,the control of shale pore structure by tectonic movements is still controversial,which limits the research progress of shale gas accumulation mechanism in the complex tectonic region of southern China.In this study,34 samples were collected from two exploratory wells located in different tectonic locations.Diverse experiments,e.g.,organic geochemistry,XRD analysis,FE-SEM,low-pressure gas adsorption,and high-pressure mercury intrusion,were conducted to fully characterize the shale reservoir.The TOC,Ro,and mineral composition of the shale samples between the two wells are similar,which reflects that the shale samples of the two wells have proximate pores-generating capacity and pores-supporting capacity.However,the pore characteristics of shale samples from two wells are significantly different.Compared with the stabilized zone shale,the porosity,pore volume,and specific surface area of the deformed zone shale were reduced by 60.61%,64.85%,and 27.81%,respectively.Moreover,the macroscopic and fine pores were reduced by 54.01%and 84.95%,respectively.Fault activity and uplift denudation are not conducive to pore preservation,and the rigid basement of Huangling uplift can promote pore preservation.These three factors are important reasons for controlling the difference in pore structure between two wells shales.We established a conceptual model of shale pores evolution under different tectonic preservation conditions.This study is significant to clarify the scale of shale gas formation and enrichment in complex tectonic regions,and helps in the selection of shale sweet spots.

Privacy-preserved learning from non-i.i.d data in fog-assisted IoT:A federated learning approach

With the prevalence of the Internet of Things(IoT)systems,smart cities comprise complex networks,including sensors,actuators,appliances,and cyber services.The complexity and heterogeneity of smart cities have become vulnerable to sophisticated cyber-attacks,especially privacy-related attacks such as inference and data poisoning ones.Federated Learning(FL)has been regarded as a hopeful method to enable distributed learning with privacypreserved intelligence in IoT applications.Even though the significance of developing privacy-preserving FL has drawn as a great research interest,the current research only concentrates on FL with independent identically distributed(i.i.d)data and few studies have addressed the non-i.i.d setting.FL is known to be vulnerable to Generative Adversarial Network(GAN)attacks,where an adversary can presume to act as a contributor participating in the training process to acquire the private data of other contributors.This paper proposes an innovative Privacy Protection-based Federated Deep Learning(PP-FDL)framework,which accomplishes data protection against privacy-related GAN attacks,along with high classification rates from non-i.i.d data.PP-FDL is designed to enable fog nodes to cooperate to train the FDL model in a way that ensures contributors have no access to the data of each other,where class probabilities are protected utilizing a private identifier generated for each class.The PP-FDL framework is evaluated for image classification using simple convolutional networks which are trained using MNIST and CIFAR-10 datasets.The empirical results have revealed that PF-DFL can achieve data protection and the framework outperforms the other three state-of-the-art models with 3%–8%as accuracy improvements.

Trusted Certified Auditor Using Cryptography for Secure Data Outsourcing and Privacy Preservation in Fog-Enabled VANETs

With the recent technological developments,massive vehicular ad hoc networks(VANETs)have been established,enabling numerous vehicles and their respective Road Side Unit(RSU)components to communicate with oneanother.The best way to enhance traffic flow for vehicles and traffic management departments is to share thedata they receive.There needs to be more protection for the VANET systems.An effective and safe methodof outsourcing is suggested,which reduces computation costs by achieving data security using a homomorphicmapping based on the conjugate operation of matrices.This research proposes a VANET-based data outsourcingsystem to fix the issues.To keep data outsourcing secure,the suggested model takes cryptography models intoaccount.Fog will keep the generated keys for the purpose of vehicle authentication.For controlling and overseeingthe outsourced data while preserving privacy,the suggested approach considers the Trusted Certified Auditor(TCA).Using the secret key,TCA can identify the genuine identity of VANETs when harmful messages aredetected.The proposed model develops a TCA-based unique static vehicle labeling system using cryptography(TCA-USVLC)for secure data outsourcing and privacy preservation in VANETs.The proposed model calculatesthe trust of vehicles in 16 ms for an average of 180 vehicles and achieves 98.6%accuracy for data encryption toprovide security.The proposedmodel achieved 98.5%accuracy in data outsourcing and 98.6%accuracy in privacypreservation in fog-enabled VANETs.Elliptical curve cryptography models can be applied in the future for betterencryption and decryption rates with lightweight cryptography operations.

A Cloud-Fog Enabled and Privacy-Preserving IoT Data Market Platform Based on Blockchain

The dynamic landscape of the Internet of Things(IoT)is set to revolutionize the pace of interaction among entities,ushering in a proliferation of applications characterized by heightened quality and diversity.Among the pivotal applications within the realm of IoT,as a significant example,the Smart Grid(SG)evolves into intricate networks of energy deployment marked by data integration.This evolution concurrently entails data interchange with other IoT entities.However,there are also several challenges including data-sharing overheads and the intricate establishment of trusted centers in the IoT ecosystem.In this paper,we introduce a hierarchical secure data-sharing platform empowered by cloud-fog integration.Furthermore,we propose a novel non-interactive zero-knowledge proof-based group authentication and key agreement protocol that supports one-to-many sharing sets of IoT data,especially SG data.The security formal verification tool shows that the proposed scheme can achieve mutual authentication and secure data sharing while protecting the privacy of data providers.Compared with previous IoT data sharing schemes,the proposed scheme has advantages in both computational and transmission efficiency,and has more superiority with the increasing volume of shared data or increasing number of participants.

Privacy-Preserving Healthcare and Medical Data Collaboration Service System Based on Blockchain and Federated Learning

As the volume of healthcare and medical data increases from diverse sources,real-world scenarios involving data sharing and collaboration have certain challenges,including the risk of privacy leakage,difficulty in data fusion,low reliability of data storage,low effectiveness of data sharing,etc.To guarantee the service quality of data collaboration,this paper presents a privacy-preserving Healthcare and Medical Data Collaboration Service System combining Blockchain with Federated Learning,termed FL-HMChain.This system is composed of three layers:Data extraction and storage,data management,and data application.Focusing on healthcare and medical data,a healthcare and medical blockchain is constructed to realize data storage,transfer,processing,and access with security,real-time,reliability,and integrity.An improved master node selection consensus mechanism is presented to detect and prevent dishonest behavior,ensuring the overall reliability and trustworthiness of the collaborative model training process.Furthermore,healthcare and medical data collaboration services in real-world scenarios have been discussed and developed.To further validate the performance of FL-HMChain,a Convolutional Neural Network-based Federated Learning(FL-CNN-HMChain)model is investigated for medical image identification.This model achieves better performance compared to the baseline Convolutional Neural Network(CNN),having an average improvement of 4.7%on Area Under Curve(AUC)and 7%on Accuracy(ACC),respectively.Furthermore,the probability of privacy leakage can be effectively reduced by the blockchain-based parameter transfer mechanism in federated learning between local and global models.