Privacy Issues Research Articles

Balancing Safety and Justice, the Ethics of Predictive Policing

Examining the ethical ramifications of predictive policing in South Africa, the research aims to pinpoint major obstacles and dangers while examining potential solutions to allay worries and guarantee responsible application. Key subjects include data privacy, algorithmic bias, over policing, community involvement, accountability and transparency, and transparency. reduction of bias, oversight procedures, Important Points, Significant ethical issues are brought up by predictive policing in South Africa, including invasions of privacy, algorithmic prejudice, and over policing. Given the historical and current backdrop of racial inequality, these worries are more pressing. In order to address these issues, a balanced strategy that puts individual rights and public safety first is needed. In order to guarantee that predictive policing is used responsibly in South Africa, transparency, accountability, community involvement, and ethical standards are crucial. It is essential to mitigate bias in algorithms and data in order to stop biased results. An over-reliance on predictive policing can be detrimental to community relations and conventional enforcement techniques. Methodological strategy: Designing qualitative research, review of the literature, semi-structured interviews with members of the public, law enforcement officers, and predictive policing specialists Case studies of South African predictive policing initiatives, Content study of South African media reports on predictive policing. Relevance. The work advances our knowledge of the moral conundrums raised by predictive policing in South Africa in a more comprehensive and nuanced way. The study can serve to raise public awareness and encourage participation in the discussion over predictive policing in South Africa. The findings can assist policymakers and law enforcement agencies in creating moral and practical strategies for implementing predictive policing. In conclusion, there are advantages and disadvantages to predictive policing in South Africa. Although technology presents the possibility of more effective and efficient law enforcement, it also brings up serious ethical issues. South Africa can minimize the dangers associated with predictive policing while maximizing its potential advantages by addressing these issues and putting the necessary procedures in place.

A Study on Web Cryptography Increase the Security of Web Applications with the Expansion of Privacy Issues and Cyberthreats

A Study on Web Cryptography Increase the Security of Web Applications with the Expansion of Privacy Issues and Cyberthreats

The centrality of nursing in realizing high quality palliative care: Exploring Canada’s framework on palliative care priorities

BackgroundFollowing an earlier mixed-method survey in which we asked stakeholders to report on their perceptions of the progress made in relation to Canada’s Framework on Palliative Care and Action Plan, the purpose of this study was to conduct an in-depth qualitative exploration of the factors influencing that progress, or lack thereof.MethodsThis was a qualitative interview study conducted in Canada. Inclusion criteria included experience with palliative care in Canada in a professional or volunteer capacity. Interviews were conducted by telephone using an interview guide that asked specific questions in relation to the Framework on palliative care priorities (e.g., education, caregiver support, and equitable access). Data was analyzed using qualitative descriptive methods.ResultsThirty-five diverse stakeholders with extensive experience in palliative care were interviewed. In relation to palliative education, participants indicated that although there were excellent palliative care resources available across the country there was further need for embedding palliative care in undergraduate education and for mentored opportunities to engage in care across diverse contexts. The identification, development, and strategic positioning of champions was an important strategy for improving palliative care knowledge and capacity. The development of standard competencies was viewed as an important step forward; although, there was a need to include more members of the care-team and to create pathways for life-long learning. In relation to support for family caregivers, even as participants cited numerous community-based resources offered by not-for-profit organizations, they described significant barriers including a shortage of in-home support, lack of understanding of what caregivers do, and policy-based contractual and privacy issues. In relation to palliative care access, participants described a nurse-centered, consult-based, multi-site and multi-provider model of care that was facilitated by technology. Barriers to this model were systemic healthcare issues of siloed, fragmented, and for-profit care.ConclusionParticipants in this study had clear insights into the factors that would support or impede progress to the development of palliative care in Canada. Some of those factors were achievable within current health and educational systems. Other factors were going to require longer term and more comprehensive solutions.

Applications and Concerns of ChatGPT and Other Conversational Large Language Models in Health Care: Systematic Review

Background The launch of ChatGPT (OpenAI) in November 2022 attracted public attention and academic interest to large language models (LLMs), facilitating the emergence of many other innovative LLMs. These LLMs have been applied in various fields, including health care. Numerous studies have since been conducted regarding how to use state-of-the-art LLMs in health-related scenarios. Objective This review aims to summarize applications of and concerns regarding conversational LLMs in health care and provide an agenda for future research in this field. Methods We used PubMed, ACM, and the IEEE digital libraries as primary sources for this review. We followed the guidance of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) to screen and select peer-reviewed research articles that (1) were related to health care applications and conversational LLMs and (2) were published before September 1, 2023, the date when we started paper collection. We investigated these papers and classified them according to their applications and concerns. Results Our search initially identified 820 papers according to targeted keywords, out of which 65 (7.9%) papers met our criteria and were included in the review. The most popular conversational LLM was ChatGPT (60/65, 92% of papers), followed by Bard (Google LLC; 1/65, 2% of papers), LLaMA (Meta; 1/65, 2% of papers), and other LLMs (6/65, 9% papers). These papers were classified into four categories of applications: (1) summarization, (2) medical knowledge inquiry, (3) prediction (eg, diagnosis, treatment recommendation, and drug synergy), and (4) administration (eg, documentation and information collection), and four categories of concerns: (1) reliability (eg, training data quality, accuracy, interpretability, and consistency in responses), (2) bias, (3) privacy, and (4) public acceptability. There were 49 (75%) papers using LLMs for either summarization or medical knowledge inquiry, or both, and there are 58 (89%) papers expressing concerns about either reliability or bias, or both. We found that conversational LLMs exhibited promising results in summarization and providing general medical knowledge to patients with a relatively high accuracy. However, conversational LLMs such as ChatGPT are not always able to provide reliable answers to complex health-related tasks (eg, diagnosis) that require specialized domain expertise. While bias or privacy issues are often noted as concerns, no experiments in our reviewed papers thoughtfully examined how conversational LLMs lead to these issues in health care research. Conclusions Future studies should focus on improving the reliability of LLM applications in complex health-related tasks, as well as investigating the mechanisms of how LLM applications bring bias and privacy issues. Considering the vast accessibility of LLMs, legal, social, and technical efforts are all needed to address concerns about LLMs to promote, improve, and regularize the application of LLMs in health care.

MAC Address Classification in Privacy Issue Using Gaussian Naïve Bayes

There have been several initiatives within standards committees to overcome privacy issues, including user tracking activity based on Media Access Control (MAC) addresses. The implementation of randomized MAC addresses on captive portals, with user-specific connection limits to address privacy concerns, introduces some problems. To address this issue, device removal based on OUI classification was proposed. Connection data taken from the RADIUS server were divided into two distinct classes, either random or not. Gaussian Naïve Bayes was utilized to classify the data with 16 distinct thresholds, and the solution with the highest accuracy was selected. The research produced results showing that all classifications had an accuracy above 96%. Values of 6 and 50% for Mac address thresholds and random percentage thresholds gave the highest accuracy of 98.1139%. This indicates that random Mac address classification in the real world can be done using the result.

Security and Privacy on Generative Data in AIGC: A Survey

The advent of artificial intelligence-generated content (AIGC) represents a pivotal moment in the evolution of information technology. With AIGC, it can be effortless to generate high-quality data that is challenging for the public to distinguish. Nevertheless, the proliferation of generative data across cyberspace brings security and privacy issues, including privacy leakages of individuals and media forgery for fraudulent purposes. Consequently, both academia and industry begin to emphasize the trustworthiness of generative data, successively providing a series of countermeasures for security and privacy. In this survey, we systematically review the security and privacy on generative data in AIGC, particularly for the first time analyzing them from the perspective of information security properties. Specifically, we reveal the successful experiences of state-of-the-art countermeasures in terms of the foundational properties of privacy, controllability, authenticity, and compliance, respectively. Finally, we show some representative benchmarks, present a statistical analysis, and summarize the potential exploration directions from each of theses properties.

Expectations vs reality: teenager views of institutional privacy

ABSTRACT Teenagers are growing up under pervasive networks of institutional surveillance. However, prior work on teens’ privacy attitudes and practices has largely focused on parental or peer surveillance. To explore how teenagers understand privacy in the context of institutional surveillance, we interviewed twelve teenagers residing in the US on location-tracking within high schools, which are primary sites of youth institutional surveillance. Using the contextual integrity framework, a structured approach to analyzing privacy, we address the following research questions: How do changes in the parameters of technology-driven information flows in high schools affect teenagers’ assessments of whether such flows are appropriate? What contextual values inform teenagers’ views of the appropriateness of technology-driven information flows in high schools? We found participants’ evaluations of institutional surveillance most often considered how the technology would impact the values of safety, autonomy, and community. We found large gaps between teenagers’ prescriptive norms and descriptive norms, which indicate that teenagers frequently experience institutional privacy violations, leading many to view such violations as inevitable and hold feelings of surveillance realism. We call for more research around young people and institutional privacy, and for teenage privacy education to engage in critical discussions and hands-on decision-making about privacy at the institutional level.

Teen Talk: The Good, the Bad, and the Neutral of Adolescent Social Media Use

The debate on whether social media has a net positive or negative effect on youth is ongoing. Therefore, we conducted a thematic analysis on 2,061 posts made by 1,038 adolescents aged 15-17 on an online peer-support platform to investigate the ways in which these teens discussed popular social media platforms in their posts and to identify differences in their experiences across platforms. Our findings revealed four main emergent themes for the ways in which social media was discussed: 1) Sharing negative experiences or outcomes of social media use (58%, n = 1,095), 2) Attempts to connect with others (45%, n = 922), 3) Highlighting the positive side of social media use (20%, n = 409), and 4) Seeking information (20%, n = 491). Overall, while sharing about negative experiences was more prominent, teens also discussed balanced perspectives of connection-seeking, positive experiences, and information support on social media that should not be discounted. Moreover, we found statistical significance for how these experiences differed across social media platforms. For instance, teens were most likely to seek romantic relationships on Snapchat and self-promote on YouTube. Meanwhile, Instagram was mentioned most frequently for body shaming, and Facebook was the most commonly discussed platform for privacy violations (mostly from parents). The key takeaway from our study is that the benefits and drawbacks of teens' social media usage can co-exist and net effects (positive or negative) can vary across different teens across various contexts. As such, we advocate for mitigating the negative experiences and outcomes of social media use as voiced by teens, to improve, rather than limit or restrict, their overall social media experience. We do this by taking an affordance perspective that aims to promote the digital well-being and online safety of youth "by design."

Integrating Blockchain Technology with Internet of Things and Edge Computing to Achieve Security

The last decade has seen many advancements and emergence in computing technologies; Internet of Things (IoT) being one of the most successful among them. Huge data generation in IoT can be utilized for analysis and monitoring the behaviour of various patterns. In spite of wide adaptability, IoT has various challenges such as privacy, security and computational constraints. To address the later challenge, Edge computing can be a potential solution with great computational resources leading towards the improvement in performance in terms of latency, throughput and response time. However, privacy and security remain largely unaddressed along with the traditional limitations of a centralized approach. This brings into the usage of another technology viz. Blockchain that handles the issue of privacy and security through its inherent features such as immutability, transparency and decentralization. In this research, we intend to explore the option of possible integration of Blockchain technology with IoT to address these challenges.

Navigating the Privacy Paradox : Balancing AI Advancement and Data Protection in the Digital Age

The rapid advancement of artificial intelligence (AI) technologies has ushered in an era of unprecedented data utilization, raising critical concerns about individual privacy. This article examines the complex interplay between AI development and data protection, exploring the challenges of balancing the need for large-scale data processing with the imperative to safeguard personal information. We analyze current regulatory frameworks, including GDPR and CCPA, and their efficacy in addressing AI-specific privacy issues. The article also evaluates technical measures such as differential privacy, federated learning, privacy-preserving machine learning algorithms, and organizational best practices for responsible data management. By synthesizing computer science, law, and ethics perspectives, we propose a multidisciplinary approach to fostering AI innovation while robustly protecting individual privacy rights. Our findings underscore the need for adaptive regulations, enhanced technical safeguards, and increased collaboration between stakeholders to navigate the evolving landscape of AI and privacy in the digital age.

THE IMPACT OF TELEMEDICINE ON ACCESS TO PRIMARY CARE

The COVID-19 pandemic has driven the implementation of telemedicine as a solution for maintaining access to healthcare, transforming the primary care landscape in many parts of the world. In Brazil, telemedicine has established itself as an essential tool for overcoming geographical and social barriers, facilitating access to basic care for populations that traditionally faced difficulties in accessing health services. This study seeks to investigate the impact of telemedicine on access to primary care, analyzing its main challenges and opportunities in the context of post-pandemic primary care. This study seeks to analyze the impact of telemedicine on access to primary care, exploring the main challenges and opportunities that arise with this modality of care. It also aims to identify practices and policies that can strengthen the implementation of telemedicine in Primary Care, ensuring that remote care is effective, safe and inclusive. This is a literature review, based on a qualitative approach, using the Scielo, Google Scholar and PubMed databases. To refine the research, the health descriptors “telemedicine”, “primary care”, “COVID-19”, and “equity in access to health” were selected, with a time frame between 2021 and 2023. Through a literature review, the study explores recent data on telemedicine in primary care, focusing on the main opportunities it offers, such as improved access and efficiency of services, as well as the challenges, including limited technological infrastructure in poor regions, privacy and confidentiality issues, and the need for adequate training for health professionals. Telemedicine enables more agile care and coverage of a larger population, but still faces obstacles related to digital accessibility and maintaining quality and continuity of care, especially for vulnerable groups. Telemedicine has therefore proved to be a strategic tool for expanding access to primary care, offering a viable alternative for reducing gaps in primary care. However, in order to maximize its impact, it is essential to overcome the technological challenges, guarantee information security and train health professionals in this new type of care. The continued use of telemedicine in the post-pandemic context presents an opportunity to strengthen the Unified Health System (SUS) in Brazil, expanding the reach of primary care and promoting greater equity in access to health.

A Study on Functional Requirements and Inspection Items for AI System Change Management and Model Improvement on the Web Platform

The rapid adoption of artificial intelligence (AI) on the web platform across multiple sectors has highlighted not only its inherent technical hurdles, such as unpredictability and lack of transparency, but also significant societal concerns. These include the misuse of AI technology, invasions of privacy, discrimination fueled by biased data, and infringements of copyright. Such challenges jeopardize the sustainable growth of AI and risk the erosion of societal trust, industry adoption and financial investment. This analysis explores the AI system’s lifecycle, emphasizing the essential continuous monitoring and the need for creating trustworthy AI technologies. It advocates for an ethically oriented development process to mitigate adverse effects and support sustainable progress. The dynamic and unpredictable nature of AI, compounded by variable data inputs and evolving distributions, requires consistent model updates and retraining to preserve the integrity of services. Addressing the ethical aspects, this paper outlines specific guidelines and evaluation criteria for AI development, proposing an adaptable feedback loop for model improvement. This method aims to detect and rectify performance declines through prompt retraining, thereby cultivating robust, ethically sound AI systems. Such systems are expected to maintain performance while ensuring user trust and adhering to data science and web technology standards. Ultimately, the study seeks to balance AI’s technological advancements with societal ethics and values, ensuring its role as a positive, reliable force across different industries. This balance is crucial for harmonizing innovation with the ethical use of data and science, thereby facilitating a future where AI contributes significantly and responsibly to societal well-being.

Biomedical moral enhancement for psychopaths.

This study examines the ethical permissibility of biomedical moral enhancement (BME) for psychopaths, considering both coercive and voluntary approaches. To do so, I will first briefly explain what psychopaths are and some normative implications of these facts. I will then ethically examine three scenarios of BME for psychopaths: (1) coercive BME for non-criminal psychopaths, (2) coercive BME for psychopathic offenders, and (3) voluntary BME for psychopathic offenders. I will argue that coercive BME for non-criminal psychopaths is ethically problematic due to issues of cost, invasion of privacy, and stigmatic effects of compulsory diagnosis. Similarly, I will argue that coercive BME for criminals is impermissible due to violations of the rights to bodily and mental integrity. However, I will show that voluntary BME for offenders may be ethically permissible under certain conditions, challenging the critique that the consent of vulnerable prisoners cannot be considered fully voluntary. I argue that when an offender is provided with sufficient medical and legal information, incentives such as the possibility of parole review based on BME results do not preclude the voluntariness of consent. Ultimately, I aim to advance the debate on BME for psychopaths by delineating and defending conditions for the ethical permissibility of voluntary BME.

ARTIFICIAL INTELLIGENCE IN CRIMINAL JUSTICE MANAGEMENT: A SYSTEMATIC LITERATURE REVIEW

This systematic review, based on 37 articles, explores the role of artificial intelligence (AI) in criminal justice, focusing on its applications in predictive policing, judicial risk assessments, and surveillance, as well as the associated ethical and regulatory challenges. AI has demonstrated substantial potential for improving efficiency and accuracy in criminal justice systems, from optimizing law enforcement resource allocation to providing data-driven risk assessments that support judicial decisions. However, the review identifies significant ethical issues, especially related to algorithmic bias, which can perpetuate existing societal inequalities and disproportionately affect marginalized communities. Concerns around transparency and accountability are prevalent, as the "black-box" nature of many AI algorithms complicates public understanding and trust in AI-driven outcomes. Surveillance tools, including facial recognition and behavioral analysis, enhance real-time threat detection but raise privacy and civil rights concerns, highlighting the need for regulatory oversight. Gaps in legal frameworks suggest the urgency for standardized policies that address data privacy, algorithmic fairness, and accountability in AI applications. The findings underscore that interdisciplinary collaboration, transparent practices, and comprehensive regulatory measures are essential to responsibly integrate AI into criminal justice, balancing technological advancements with justice, equity, and public trust.

Implementasi Artificial Intelligence dalam Rekrutmen: Manfaat dan Tantangan di Industri 4.0

This study aims to explore the implementation of Artificial Intelligence (AI) in the recruitment process in the era of Industry 4.0, focusing on the benefits and challenges faced by companies. Utilizing a qualitative approach through in-depth interviews with recruitment teams, human resource managers, and candidates, the research finds that the adoption of AI brings several advantages, including enhanced efficiency in the selection process, improved screening accuracy, and an enriched candidate experience. However, significant challenges also arise, such as privacy and data security issues, a lack of transparency in algorithms, and regulatory uncertainties that may affect the adoption of this technology. The findings highlight the need for companies to address these challenges through the development of robust data protection policies, regular monitoring of algorithms, and educating both candidates and recruitment teams about AI usage. This research aims to provide insights for organizations in implementing AI ethically and effectively in the recruitment process.

Quantum-assisted federated intelligent diagnosis algorithm with variational training supported by 5G networks

In the realm of intelligent healthcare, there is a growing ambition to reshape medical services through the integration of artificial intelligence (AI). However, conventional machine learning faces inherent challenges such as privacy issues, delayed updates, and protracted training times, particularly due to the hesitance of medical institutions to directly share sensitive data, with possible noises. In response to these concerns, a Quantum-Assisted Federated Intelligent Diagnosis Algorithm (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta $$\\end{document}-QuAFIDA) is proposed, applied into real medical data. Leveraging the capabilities of the 5G mobile network, this approach works the connection between Internet of Medical Things (IoMT) devices through the 5G, synchronizing training and updating the server model without disrupting their real-world applications. In our quest to safeguard patient data and enhance training efficiency, our study employs an innovative heuristic approach marked by a nested loop structure. Specifically, the inner loop is dedicated to training the beta-variational quantum eigensolver (β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta $$\\end{document}-VQE) to approximate the expectation values of the proposed algorithm; the outer loop trains the β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta $$\\end{document}-QuAFIDA to reduce the relative entropy towards the target. This approach involves a balance between privacy considerations and the urgency of training. Results demonstrate that representations with low-rank attained through β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta $$\\end{document}-QuAFIDA offer an effective approach for acquiring low-rank states. This research signifies a step forward in the synergy between AI and 5G technologies, presenting a novel avenue for the advancement of intelligent healthcare.

Privacy during pandemics: Attitudes to public use of personal data

In this paper we investigate people’s attitudes to privacy and sharing of personal data when used to help society combat a contagious disease, such as COVID-19. Through a two-wave survey, we investigate the role of personal characteristics, and the effect of information, in shaping privacy attitudes. By conducting the survey in Norway and Sweden, which adopted very different strategies to handle the COVID-19 pandemic, we analyze potential differences in privacy attitudes due to policy changes. We find that privacy concern is negatively correlated with allowing public use of personal data. Trust in the entity collecting data and collectivist preferences are positively correlated with this type of data usage. Providing more information about the public benefit of sharing personal data makes respondents more positive to the use of their data, while providing additional information about the costs associated with data sharing does not change attitudes. The analysis suggests that stating a clear purpose and benefit for the data collection makes respondents more positive about sharing. Despite very different policy approaches, we do not find any major differences in privacy attitudes between Norway and Sweden. Findings are also similar between the two survey waves, suggesting a minor role for contextual changes.

Time-constrained persistent deletion for key-value store engine on ZNS SSD

The inherent out-of-place update characteristic of the Log-Structured Merge tree (LSM tree) cannot guarantee persistent deletion within a specific time window, leading to potential data privacy and security issues. Existing solutions like Lethe-Fade ensure time-constrained persistent deletion but introduce considerable write overhead, worsening the write amplification issue, particularly for key–value stores on ZNS SSD. To address this problem, we propose a zone-aware persistent deletion scheme for key–value store engines. Targeting mitigating the write amplification induced by level compaction, we design an adaptive SSTable selection strategy for each level in the LSM tree. Additionally, as the SSTable with deletion records would become invalid after the persistent deletion timer reaches its threshold, we design a tombstone-aware zone allocation strategy to reduce the data migration induced by garbage collection. In further, we optimize the victim zone selection in GC to reduce the invalid migration of tombstone files. Experimental results demonstrate that our scheme effectively ensures that most outdated physical versions are deleted before reaching the persistent deletion time threshold. When deleting 10% of keys in the key–value store engine, this scheme reduces write amplification by 74.7% and the garbage collection-induced write by 87.3% compared to the Lethe-Fade scheme.

The Sharing Energy Storage Mechanism for Demand Side Energy Communities

Energy storage (ES) units are vital for the reliable and economical operation of the power system with a high penetration of renewable distributed generators (DGs). Due to ES’s high investment costs and long payback period, energy management with shared ESs becomes a suitable choice for the demand side. This work investigates the sharing mechanism of ES units for low-voltage (LV) energy prosumer (EP) communities, in which energy interactions of multiple styles among the EPs are enabled, and the aggregated ES dispatch center (AESDC) is established as a special energy service provider to facilitate the scheduling and marketing mechanism. A shared ES operation framework considering multiple EP communities is established, in which both the energy scheduling and cost allocation methods are studied. Then a shared ES model and energy marketing scheme for multiple communities based on the leader–follower game is proposed. The Karush–Kuhn–Tucker (KKT) condition is used to transform the double-layer model into a single-layer model, and then the large M method and PSO-HS algorithm are used to solve it, which improves convergence features in both speed and performance. On this basis, a cost allocation strategy based on the Owen value method is proposed to resolve the issues of benefit distribution fairness and user privacy under current situations. A case study simulation is carried out, and the results show that, with the ES scheduling strategy shared by multiple renewable communities in the leader–follower game, the energy cost is reduced significantly, and all communities acquire benefits from shared ES operators and aggregated ES dispatch centers, which verifies the advantageous and economical features of the proposed framework and strategy. With the cost allocation strategy based on the Owen value method, the distribution results are rational and equitable both for the groups and individuals among the multiple EP communities. Comparing it with other algorithms, the presented PSO-HS algorithm demonstrates better features in computing speed and convergence. Therefore, the proposed mechanism can be implemented in multiple scenarios on the demand side.

Federated Learning for Personalized Financial Recommendations

Abstract: Federated Learning (FL) has been the solution to one of those biggest contributors that have scared us from using Machine learning, i.e. Privacy [ for sensitive domains like finance ]. This survey focuses on leveraging Federated Learning in creating personalized recommendation systems for financial products such as loans, investment plans, credit cards and savings. For example, classical recommendation systems usually work in a centralized way to store a lot of sensitive financial data (or derivative structures), this setting presents other well-known privacy issues and security risks. FL provides a solution that enables multiple financial institutions to work together to train a global recommendation model without the need any of them to share their raw customer data. The paper reviews federated learning, and some key take ways are on differential privacy and secure aggregation to protect customer data while improving the quality of recommendations. We also talk about how to solve some problems like heterogeneity of the data, model convergence and regulatory constraints required in financial methods. The paper concludes by detailing future directions for federated learning in finance, with focus on how personalized financial recommendations can be dramatically transformed while preserving user privacy.