Individual Clients Research Articles

The cyber-industrialization of catfishing and romance fraud

We examine a new form of online fraud, which we refer to as Intimacy Manipulated Fraud Industrialization (IMFI). This type of fraud bears a strong resemblance to traditional online romance fraud and catfishing, but is “industrialized” through enterprise business practices, software platforms, and customer service processes. To gain a better understanding of this operation, we conducted an inductive analysis of publicly available testimonial and review data provided by current and prior employees of a specific company in the online customer service contract space. Companies hire individuals online to work as “chat moderators” or “customer service providers” who are told that their task is to advance engagement on social media platforms. In fact, they are being recruited as “sexting” workers, paid on a per-text basis to engage in intimate chatting with clients who believe they're interacting with individuals of the opposite gender on a dating site. The process is mediated via client management processes that monitor employee productivity and monetize all interactions between “clients” and “workers.” The company executes these processes with great efficiency by algorithmically assigning multiple workers to individual clients and assembling background files on clients in real time. We find that workers serve as both exploiters of their clients as well as victims of the company they work for. The implications of our study could significantly impact how we address AI-generated online fraud in the future, shedding light on the complex dynamics at play within these fraudulent enterprises.

AutoFL: A Bayesian Game Approach for Autonomous Client Participation in Federated Edge Learning

Given that devices (i.e., clients) participating in federated edge learning (FEL) are autonomous and resource-constrained in nature, it is critical to design effective incentive mechanisms to encourage client participation so as to improve the performance of FEL. In this paper, we aim to boost the FEL training efficiency by answering how much compute resource should clients autonomously contribute to maximize their utilities. To this end, we develop AutoFL, an autonomous client participation decision framework for federated learning at the network edge without assuming that each client possesses complete information. We first model the problem of autonomous client participation as a Bayesian game with incomplete information, where each player in the game is associated with a set of types according to network conditions. We optimize an individual client's decision based on the dynamics of the population estimated following the Bayes rule. We prove that AutoFL can converge to a unique Bayesian Nash equilibrium point. Empirical results on three real datasets show that AutoFL achieves a higher model accuracy with only 15.5-24.5% model aggregation time per global training round, and its energy cost saving on mobile devices is 82.2-86.8% compared to the state-of-the-art algorithms. Moreover, we can achieve a 2.75-3.2x long-term fairness compared to classical solutions.

Insurance Services and Protection of Economic Resources of Production in Rwanda in Sonarwa

The focus of this study was to assess the contribution of insurance services in the protection of economic resources of production, taking SONARWA Insurance Company as a case study. The study used a descriptive method whereby both qualitative and quantitative data were sought. The target population consisted of managers in public companies, private companies, semi-public companies, NGOs as well as individual clients who are experienced and paid a considerable premium and also employees of Sonarwa General who are managers and employees working in different departments. The total population came to 104 insured clients including 25 staff respondents from Sonarwa General in Kigali City. Slovin’s formula was used to calculate the sample size of 62 respondents of whom questionnaires were distributed to them to receive their views. The researcher designed a special interview schedule with insured clients using random sampling as well as top managers using purposive sampling. The data analysis was done using tables generated from SPSS. It was found that there was the effectiveness of insurance services in protecting economic resources as 21.0% of respondents said that quick compensation is one of the elements that make the insurance services of Sonarwa General very effective because the insured restart quickly their activities and continue its course of productivity. On the impact of insurance services from SONARWA on the sustainability of economic resources of the production of insured, 33.9% said that insurance services protect economic resources through the insurance of goods and properties, 17.7% for liability insurance, and 21.0% for financial operations and bid bonds. On the development of various insurance products and provision of opportunities to secure different types and categories of assets of the insured, 26 (41.9%) of respondents agreed that SONARWA-developed services and products protect the resources of the insured to about a tune of 61% to 80% risk protection against internal and external threats to be able to protect the economic resources of production of its clients. In addition, 24.2% of respondents were contented with the way Sonarwa identified major risks that may affect the economic resources of the insured so that it could establish appropriate ways to properly protect the economic resources of the insured against probable risks. Keywords: Insurance services, SONARWA, Insurance Companies, Economic resources, Insured.

Anticipating multisectoral use of services with the support of AI

Introduction: This paper presents the preliminary results of a collaborative R&D project which aims at developing artificial intelligence (AI) supported anticipation of multisectoral use of services. If we were able to predict the escalation of health and social problems of clients and the use of several different services, we could plan and offer them early preventive services with the objective of improving the quality of life and reducing the costs of service provision in the longer term.
 Approach and methods: The multidisciplinary project in progress collaborates at four spheres of research and development within the elderly care of one welfare region in Finland.
 1) Anticipatory management practices concerning risk client groups and anticipatory case management practices concerning individual clients in risk are being developed supported by predictive AI technology. The requirements concerning the information the AI based prediction model should produce to the managers and to the case managers have provisionally been defined. The current practices are co-studied, and the new practices supported by AI are co-designed by involving the “relevant” health and social care managers and practitioners in the welfare region.
 2) A machine learning (ML) predictive model based on health and social care data is being developed. The prediction model will be developed based on retrospective analysis of health and social data of the welfare region. The available data includes clinical data recorded during healthcare encounters, decisions, and usage of social services as well as physical function assessments. The data is used to train and test potential machine learning algorithms for predicting future service use of the elderly individuals based on their current health status and past use of services.
 3) The implementation of the AI/ML model within the IT infrastructure and information systems (IS) in use will be supported and investigated. The developed ML model would eventually be integrated into the IT/IS environment of the case organization. That entails connecting the specific data sources, running the model computations, and passing the results to the digital workflow of the care production management for knowledge management.
 
 4) The EU and Finnish legislation that regulate the use of personal health and social data in the development and use of AI based predictive models is being analyzed. Requirements and potential limitations imposed by current legislation on the use of predictive models are identified. In particular, the strict conditions applicable to making automated risk assessments of individuals for purposes of taking anticipatory measures are analyzed and avenues for meeting them by health and social care organizations are discussed.
 Results and outputs: Working on these four spheres, the project produces a generic model on developing the anticipation practices of multisectoral use of services with the help of AI technology. The model will available to all the organizations which are developing AI based anticipation of multisectoral use of services.
 Key words: Anticipation, prediction, health and social services usage, machine learning model, AI software, legislation, elderly care

The implementation of I.ROC as a way to use client goals as drivers to organise mental health care and improve mental health care through outcome monitoring.

De MaRe uses the Indivdual recovery outcome counter (I.ROC) as a way to organise mental health care starting from the individual client needs and goals. Clients are put in the drivers seat of their own recovery proces by being able to set their goals on the HOPE-framework (home, opportunity, people, empowerment) and determing their own needs in health care. Health care workers developed a toolkit to meet clients needs and facilitate the recovery proces.
 By processing the data the health care facility can use generalised input as an outcome monitor and improve the health care service for clients.
 Generalised data can also be used to benchmark the provided care with peer centers in Flanders

A federated distillation domain generalization framework for machinery fault diagnosis with data privacy

Federated learning is an emerging technology that enables multiple clients to cooperatively train an intelligent diagnostic model while preserving data privacy. However, federated diagnostic models still suffer from a performance drop when applied to entirely unseen clients outside the federation in practical deployments. To address this issue, a Federated Distillation Domain Generalization (FDDG) framework is proposed for machinery fault diagnosis. The core idea is to enable individual clients to access multi-client data distributions in a privacy-preserving manner and further explore domain invariance to enhance model generalization. A novel diagnostic knowledge-sharing mechanism is designed based on knowledge distillation, which equips multiple generators to augment fake data during the training of local models. Based on generated data and real data, a low-rank decomposition method is utilized to mine domain invariance, enhancing the model's ability to resist domain shift. Extensive experiments on two rotating machines demonstrate that the proposed FDDG achieves a 3% improvement in accuracy compared to state-of-the-art methods.

FORMATION OF A SYSTEM APPROACH TO ORGANIZING CARGO DELIVERY BY RAILWAY COMPANIES-CARRIER REGIONAL TYPE

Purpose. The introduction of private freight railway carrier companies in Ukraine corresponds to the European trend of demonopolization of railway transport and has a number of consequences, including the creation of a market pricing mechanism and the formation of prerequisites for improving the quality of services in railway transport. In order to ensure the economic development of the railway industry, an integrated approach is required, which includes reviewing and improving the tariff policy regarding the access of private regional railway carrier companies to the railway infrastructure of joint-stock company (JSC) «Ukrzaliznytsia» and providing non-discriminatory access to the railway infrastructure for other transportation participants. This will ensure equal conditions for competition and will contribute to the development of railway transport in Ukraine. Based on this, the purpose of this study is to achieve the effective functioning of a cargo delivery system for regional railway carrier companies when it is implemented on the Ukrainian railway network. To achieve this goal, a functional description of the specified system is used and its parameters are optimized. Methods. To formalize the system of cargo delivery by a regional railway carrier company, used methods of systems theory. The results. The research carried out made it possible to formalize the system of cargo delivery through a regional railway carrier company. In the process of formulating the functional description of the system, various factors affecting the carrier company's costs were taken into account. When analyzing these factors, it was found that the key parameters of the system that have a significant impact on the costs and cost of transporting goods are the serial number of the cargo delivery route, the number of stops on the route, the duration of train downtime at the railway stations of the carrier company's branches while waiting for shunting operations to be performed (attaching groups of wagons). The goal of optimizing these parameters is to increase the efficiency of the system and reduce the cost of transporting goods for individual clients. Practical significance. Subject to the adoption in Ukraine of an appropriate legislative framework that will regulate access to the railway infrastructure of JSC «Ukrzaliznytsia» for private carriers, the implementation of the proposed system will have such positive consequences as increasing the level of competition in the transport market in Ukraine, improving the quality and reliability of transportation and growth Country's GDP. Setting the optimal balance between route numbers, the number of stops and the duration of train downtime will ensure optimal use of the carrier company's resources and reduce the cost of transporting goods. This will help improve the quality of service and meet customer needs.

Consumption prediction with privacy concern: Application and evaluation of Federated Learning

In this paper, we propose privacy-friendly electricity consumption prediction models based on Federated Learning (FL). Federated Learning provides a novel framework for Artificial Neural Network training. It decouples data storage from model training from decentralized data sources. A central server does not need to collect raw training data from individual clients but only the model parameters, like the gradients or weights updates. The sensitive raw data can be safely stored and used by end-users themselves. We improve the accuracy of the FL model by first clustering households, and training a personalized model for each cluster. We also analyse the Deep Leakage from Gradients (DLG) attack in our study case with three scenarios. Our simulations suggest that the DLG attack can barely succeed in consumption prediction. In this way, the FL model can guarantee clients’ privacy by design. We use a large-scale dataset that contains 3590 households’ 1.5 years of consumption to test the FL model’s performance. Several clustering algorithms are tested for the following experiments. To comprehensively test the FL model’s performance, we propose several popular neural network models: the simple Deep Neural Network, Long Short-Term Memory, Convolutional Neural Network, and WaveNet. These models are both trained under the centralized and federated framework. The federated trained models slightly sacrifice the model’s accuracy while guaranteeing the client’s data privacy. Meanwhile, the federated model shows remarkable scalability. Under the FL framework, new clients can obtain their prediction 6 times faster. Moreover, the federated model has strong robustness against missing or damaged training data. With a certain percentage of missing data in the training set, the centralized model’s accuracy gets 27% worse, while the federated model’s accuracy only gets 2% worse.

To what extent are early alliance perceptions a function of romantic partners' initial expectations for couple therapy?

AbstractIn this study, we investigated the association between clients' initial outcome expectations and their subsequent perceptions of the expanded therapeutic alliance. Romantic partners (N = 252) who received at least four sessions of systemic couple therapy from thirty‐one therapists from the Marriage and Family Therapy Practice Research Network (Johnson et al., 2017; www.mft‐prn.net) completed an outcome expectation measure before session 1 and a therapeutic alliance measure before session 4. Results showed a strong association between expectations and alliance (r = 0.51). While fourteen per cent of the variability in session 4 alliance scores was uniquely attributable to therapists, 31.6 per cent of the variability in the expectations/alliance association was uniquely attributable to couples, with only 6.1 per cent uniquely attributable to individual clients. Taken together, these results suggest that, while some therapists are better at developing strong alliances, couple and client factors associated with expectations for therapy set the stage for how the expanded alliance develops.

Impact of federated deep learning on vehicle-based speed control in mixed traffic flows

This study investigates the application of Federated Learning (FL) in an environment of mixed traffic flow with Connected and Automated Vehicles (CAVs). The focus of this study is set on the CAV cruise control speed adjustment which is enforced by the Intelligent Speed Adaptation (ISA) system. It is modelled as an Actor-Critic-based learning architecture with the goal of computing the vehicle speed based on the data of the nearby vehicles. Some CAVs achieve poor travel time performance in comparison to others. Thus, the proposed FL framework selects periodically best-performing CAVs which are local clients in the context of FL. The updated global model is computed based on the weighted averaging of the best-performing models of clients. The use case environment is modelled as a simulation of a synthetic motorway with an induced capacity drop in the form of a work-zone under moderate and high traffic demand. It is shown that the FL framework can stabilise the individual client learning convergence and reduce their travel time compared to the local learning approach. The overall motorway throughput is also increased by the proposed FL framework. This indicates that the global model of FL can utilise the optimal ratio between generalisation and bias towards the most effective control policy of individual speed control. Results show that those effects are more prominent under moderate traffic demand.

Новое в защите банковских счетов от мошенников

Th is summer, the Russian Parliament adopted Federal Law No. 369-FZ, which significantly improved the legal mechanism for combating the theft of funds from the accounts of individual clients, and also established a procedure for the return of funds already debited from their accounts by fraudsters.

Therapists' and counsellors' perceptions and experiences of offering online therapy during COVID‐19: A qualitative survey

AbstractObjectiveThe aim of this research was to understand counsellors' and therapists' perceptions and experiences of working online during the COVID‐19 pandemic.MethodFive hundred and ninety clinicians, mostly UK‐based, responded to an online qualitative survey, which allowed data to be gathered from a broader range of participants than is typical for qualitative interviews or focus group studies, and provided a wide‐angle lens. The survey generated over 130,000 words, on which a five‐staged framework analysis was conducted. Seven superordinate themes were identified.ResultsIn this paper, three of these superordinate themes specifically addressing online therapeutic practice with individual adult clients are presented. Therapists' accounts addressed the diverse ways in which the online space changed how they thought about the therapy relationship and their interactions with clients. Respondents described instances where online therapy had been beneficial for facilitating and cultivating the therapeutic process and relationship as well as how online therapy could have a potentially disruptive impact on therapeutic practice.ImplicationsFor practitioners who continue to deliver therapy solely online and/or offer hybrid services, this study identifies the specific knowledge and skills required for effective and safe online therapeutic work.

‘You drew my tears’: attunement in making response art alongside the client

ABSTRACT Background: During lockdown, I began exploring the use of response art while working with individual adult clients in private practice online. At times, the contributions it made to the therapy seemed significant and too pivotal to ignore. Context: Adult clients in private art therapy practice in the UK. Approach: An overview of the present discourse on response art is provided, followed by an exploration of related theories including Stern’s ‘attunement’, Winnicott’s ‘holding’ and Bion’s ‘container-contained’. An outline of how response art is integrated into a session is presented and illustrated with three vignettes. Outcomes: Response art was useful for the clients included in this paper when frozen emotionally or struggling to find words. It helped with restarting art making, trusting the therapist, reframing experiences, and encouraging emotional processing. Conclusions: Attunement was key in the decision-making and implementation of a creative response. The therapist’s vulnerability in exposing their creative and mental processes appeared to be a valuable model for the client. The sounds (or silences) and gestures made during the making of the response art also appeared to be significant for the clients. Implications for research: Further research into benefits, risks and influencing factors when using response art would be instructive.

An Improved Big Data Analytics Architecture Using Federated Learning for IoT-Enabled Urban Intelligent Transportation Systems

The exponential growth of the Internet of Things has precipitated a revolution in Intelligent Transportation Systems, notably in urban environments. An ITS leverages advancements in communication technologies and data analytics to enhance the efficiency and intelligence of transport networks. At the same time, these IoT-enabled ITSs generate a vast array of complex data classified as Big Data. Traditional data analytics frameworks need help to efficiently process these Big Data due to its sheer volume, velocity, variety, and significant data privacy concerns. Federated Learning, known for its privacy-preserving attributes, is a promising technology for implementation within ITSs for IoT-generated Big Data. Nevertheless, the system faces challenges due to the variable nature of devices, the heterogeneity of data, and the dynamic conditions in which ITS operates. Recent efforts to mitigate these challenges focus on the practical selection of an averaging mechanism during the server’s aggregation phase and practical dynamic client training. Despite these efforts, existing research still relies on personalized FL with personalized averaging and client training. This paper presents a personalized architecture, including an optimized Federated Averaging strategy that leverages FL for efficient and real-time Big Data analytics in IoT-enabled ITSs. Various personalization methods are applied to enhance the traditional averaging algorithm. Local fine-tuning and weighted averaging tailor the global model to individual client data. Custom learning rates are utilized to boost the performance further. Regular evaluations are advised to maintain model efficacy. The proposed architecture addresses critical challenges like real-life federated environment settings, data integration, and significant data privacy, offering a comprehensive solution for modern urban transportation systems using Big Data. Using the Udacity Self-Driving Car Dataset foe vehicle detection, we apply the proposed approaches to demonstrate the efficacy of our model. Our empirical findings validate the superiority of our architecture in terms of scalability, real-time decision-making capabilities, and data privacy preservation. We attained accuracy levels of 93.27%, 92.89%, and 92.96% for our proposed model in a Federated Learning architecture with 10 nodes, 20 nodes, and 30 nodes, respectively.

Enacting multisectoral service chains and packages in the health and social care regions in Finland

Abstract Several studies have concluded that about 10% of the users of the health care and social services use most services and produce about 80% of the costs of care. However, this client group and their needs for services, which are often complex and multisectoral, are poorly characterized. The new Act on Organizing Health and Social Care Services in Finland obliges the health and social care regions to identify the client groups who need integrated services and to define the multisectoral service chains and packages for these clients. The assumption is that an individual client's personal service path can be planned and enacted by utilizing the pre-defined service chains and packages. This study aimed at studying the definition, development and enactment of the service chains and packages. The study was based on a survey which was carried out in the 22 health and social care regions in spring 2023 for analyzing 1) to which client groups the service chains and packages are defined, 2) what needs there are in the background of defining service chains and packages, 3) what kind of goals are defined for the service chains and packages, 4) what the current developmental state of the service chains and packages is and how they manage to cross the sectoral and disciplinary boundaries, and 5) what successes and challenges there are in defining, developing and enacting the service chains and packages. The survey was the first part of a study which focuses on the development and enactment of service chains and packages in the health and social care regions. The survey results showed that most of the development activities were in the definition phase. The survey gives perspective and background knowledge to the second part of the study which focuses on one specific client group, the children with neuropsychiatric symptoms, and on the definition and enactment of their service chains and packages within three regions.

Transformer training strategies for forecasting multiple load time series

In the smart grid of the future, accurate load forecasts on the level of individual clients can help to balance supply and demand locally and to prevent grid outages. While the number of monitored clients will increase with the ongoing smart meter rollout, the amount of data per client will always be limited. We evaluate whether a Transformer load forecasting model benefits from a transfer learning strategy, where a global univariate model is trained on the load time series from multiple clients. In experiments with two datasets containing load time series from several hundred clients, we find that the global training strategy is superior to the multivariate and local training strategies used in related work. On average, the global training strategy results in 21.8% and 12.8% lower forecasting errors than the two other strategies, measured across forecasting horizons from one day to one month into the future. A comparison to linear models, multi-layer perceptrons and LSTMs shows that Transformers are effective for load forecasting when they are trained with the global training strategy.

Business Environment Using Evaluation Based on Distance from Average Solution (EDAS) Method

Business Environment the term "business environment" refers to the entirety of all individuals, organizations, and other influences that are independent of the industry but may have an impact on its output. "Much like the universe, deduct from it in the subset as depicts that system, and the remaining is the environment," writes an unknown source. As a result, an organization's environment also includes the economic, cultural, governmental, technological, and other influences at play outside of it. Its environment consists of external factors such as the media, courts, customer groups, competitors, individual clients, or organizations facing management. Business operations, in contrast to ours, do not reside in a prison. Each organization is not even an end unto itself; it develops, survives, and thrives under the restrictions imposed by its particular environment and forces. Even though a single system can delicately modify or control these pressures, it is forced to respond or adapt as necessary. Business managers can recognize and assess external pressures more effectively if they have a deeper understanding of their environment. The term "business environment" refers to the whole of all the individuals, organizations, and other influences that are independent of the industry but may have an impact on its output. The business environment aids in planning, identifying business possibilities, utilizing efficient resources, and enhancing the enterprise's general performance, expansion, and profitability. Business environments come in a variety of shapes and sizes, including macro and micro environments. The presence of both the government and industry in the nation's numerous economic operations defines the business climate in India. As a result, numerous national economic policies would encourage the expansion of both segments in diverse industries. The term "environment" refers to the entirety of all alive and pro components that have an impact on human life and its outcomes. Non-living or non-biological elements are water, land, sunshine, rocks, and air, whereas all live or biological ingredients do become animals, plants, forests, fish, and birds.based on the distance from the mean solution evaluation (EDAS) is a new and efficient MCDM is proper. In this way alternatives are preferred based on their distance from the mean solution is determined. From the analysis in which EDAS (Avg evaluation based on distance from solution) method is the best solution. Short range and negative the ideal is the solution with the longest distance from the solution determines, but of these distances the comparison is not significant. Procedures, Time, Cost, Profit Tax Starting a Business, Dealing with Construction Permits, Getting Electricity, Registering Property, Getting Credit, Paying Taxes. From the result it is seen that Dealing with Construction Permitsis got the first rank where as is the Getting Creditis having the lowest rank.the first ranking dealing with Construction Permits is obtained with the lowest quality of Getting Credit.

Provider-led community antiretroviral therapy distribution in Malawi: Retrospective cohort study of retention, viral load suppression and costs.

Outcomes of community antiretroviral therapy (ART) distribution (CAD), in which provider-led ART teams deliver integrated HIV services at health posts in communities, have been mixed in sub-Saharan African countries. CAD outcomes and costs relative to facility-based care have not been reported from Malawi. We performed a retrospective cohort study in two Malawian districts (Lilongwe and Chikwawa districts), comparing CAD with facility-based ART care. We selected an equal number of clients in CAD and facility-based care who were aged >13 years, had an undetectable viral load (VL) result in the last year and were stable on first-line ART for ≥1 year. We compared retention in care (alive and no period of ≥60 days without ART) using Kaplan-Meier survival analysis and Cox regression and maintenance of VL suppression (<1,000 copies/mL) during follow-up using logistic regression. We also compared costs (in US$) from the health system and client perspectives for the two models of care. Data were collected in October and November 2020. 700 ART clients (350 CAD, 350 facility-based) were included. The median age was 43 years (IQR 36-51), median duration on ART was 7 years (IQR 4-9), and 75% were female. Retention in care did not differ significantly between clients in CAD (89.4% retained) and facility-based care (89.3%), p = 0.95. No significant difference in maintenance of VL suppression were observed between CAD and facility-based care (aOR: 1.24, 95% CI: 0.47-3.20, p = 0.70). CAD resulted in slightly higher health system costs than facility-based care: $118/year vs. $108/year per person accessing care; and $133/year vs. $122/year per person retained in care. CAD decreased individual client costs compared to facility-based care: $3.20/year vs. $11.40/year per person accessing care; and $3.60/year vs. $12.90/year per person retained in care. Clients in provider-led CAD care in Malawi had very good retention in care and VL suppression outcomes, similar to clients receiving facility-based care. While health system costs were somewhat higher with CAD, costs for clients were reduced substantially. More research is needed to understand the impact of other differentiated service delivery models on costs for the health system and clients.

Adaptive federated few-shot feature learning with prototype rectification

Targeting to produce new features from limited data, few-shot feature generation approaches have attracted extensive attention and successfully mitigated the high cost of acquiring sufficient data. However, two main challenges remain underexplored among existing few-shot feature generation methods, namely the distribution gaps between base and novel classes, and the gradual tightening of data privacy. In order to ameliorate the performance drop induced by the distribution gap and alleviate the laborious cost of collecting massive data, in this paper, we propose a novel few-shot feature generation model that integrates domain alignment, prototype rectification, and federated learning into a unified framework. Concretely, the distance between across different classes is explicitly shrunk via domain alignment, facilitating more precise and reliable feature generation. Additionally, we develop prototype correction to reduce the intra-class discrepancy and make samples from the same class more clustered. Such that, the negative effects of the boundary samples are eliminated and thus boost the model performance. Finally, we combine our few-shot feature generation with the federated framework to protect data privacy and propose an adaptive federated scheme to provide customized services for individual clients. Extensive experiments are performed on three standard benchmark datasets to evaluate the effectiveness and superiority of our proposed method. The results consistently demonstrate that our proposed model gains substantial performance boosts and achieves state-of-the-art performance on the few-shot tasks.

Statement Recognition of Access Control Policies in IoT Networks.

Access Control Policies (ACPs) are essential for ensuring secure and authorized access to resources in IoT networks. Recognizing these policies involves identifying relevant statements within project documents expressed in natural language. While current research focuses on improving recognition accuracy through algorithm enhancements, the challenge of limited labeled data from individual clients is often overlooked, which impedes the training of highly accurate models. To address this issue and harness the potential of IoT networks, this paper presents FL-Bert-BiLSTM, a novel model that combines federated learning and pre-trained word embedding techniques for access control policy recognition. By leveraging the capabilities of IoT networks, the proposed model enables real-time and distributed training on IoT devices, effectively mitigating the scarcity of labeled data and enhancing accessibility for IoT applications. Additionally, the model incorporates pre-trained word embeddings to leverage the semantic information embedded in textual data, resulting in improved accuracy for access control policy recognition. Experimental results substantiate that the proposed model not only enhances accuracy and generalization capability but also preserves data privacy, making it well-suited for secure and efficient access control in IoT networks.