Search Results (2,983)

Confidential ledgers cannot usually be pooled across entities, yet generic private federated learning does not preserve the identities that make accounting data meaningful. This paper develops Balance-Aware Federated Analytics (BAFA), a constrained federated framework that combines voucher-level differential privacy, debit–credit and period-continuity regularization, account-hierarchy smoothing, secure aggregation, and a one-sided balance-aware update correction. The formulation defines neighboring ledgers by replacement of one complete voucher, bounds the sensitivity of the released representation, model update, and compressed balance sketch, and composes one cached representation release and all round-level aggregate releases with a Rényi differential-privacy accountant that explicitly models the minimum number of non-colluding noise contributors. It also specifies period-complete aggregation for multi-line vouchers, derives the one-sided correction from a half-space projection, and gives first-order balance-safety, hierarchy-stability, convergence, and complexity results under non-IID data, clipping, privacy noise, and sketch error. Our experiments use PaySim, IEEE-CIS Fraud Detection, and UCI Online Retail transformed into accounting-style multi-entity ledgers. The reported points indicate that BAFA improves predictive utility and normalized balance consistency relative to private federated baselines while keeping membership-inference attack AUC near random guessing. The transformed-ledger evaluation is intended as controlled evidence; validation on native enterprise ledgers remains necessary. Full article

The rapid growth of AI-driven workloads, IoT ecosystems, and distributed digital services has exposed fundamental limitations in existing cloud and edge infrastructures, particularly in guaranteeing robust data privacy under emerging quantum threats. Current blockchain-based systems provide integrity and decentralization but rely predominantly on computational cryptography and access-control mechanisms, leaving them vulnerable to future quantum adversaries and large-scale inference attacks. In this paper, we introduce Data Communities as a novel paradigm for privacy-preserving, blockchain-enabled cooperative digital infrastructures, formalized within the Cooperative Digital Infrastructure (CDI) framework. Our approach integrates three complementary privacy protection layers: (i) MuReQua, a quantum-resilient blockchain consensus mechanism leveraging CQKD for cryptographic robustness against Shor-type attacks; (ii) DeSSE, an information-theoretically secure distributed storage model based on n × m fragmentation, ensuring zero information leakage below reconstruction thresholds; and (iii) a multi-tier data sovereignty model (C0–C3) enforcing policy-driven data locality and regulatory compliance across federated nodes. We formalize privacy guarantees through an adversarial model encompassing classical, quantum, insider, and governance-level threats, and demonstrate that the proposed architecture achieves information-theoretic confidentiality, forward secrecy, and attack-resilient distributed governance. A privacy leakage analysis shows that the probability of data reconstruction under sub-threshold compromise is identical to zero, outperforming conventional blockchain storage models based on encryption alone. Simulation and case study results indicate that Data Communities achieve up to 99.999% service availability, 55% reduction in external data exposure, and 22–35% carbon-aware optimization, while maintaining strict privacy guarantees across distributed environments. Compared with existing blockchain systems (e.g., Ethereum, Hyperledger Fabric), the proposed framework shifts privacy protection from access-control and pseudonymity to structural, information-theoretic privacy by design. Overall, the results establish Data Communities as a scalable and quantum-resilient foundation for next-generation privacy-preserving blockchain infrastructures, bridging distributed AI, secure storage, and cooperative governance under a unified formal model. Full article

Co-Creative Robotics combines computational creativity, robotic embodiment, and human–robot collaboration to support or generate creative behavior in physical and social environments. As these systems become more autonomous, data-intensive, and interactive, cybersecurity and privacy can no longer be treated as external safeguards added after creative functionality has been designed. This PRISMA-informed review investigates whether principles of cybersecurity-by-design and privacy-by-design can be integrated into Co-Creative Robotics without constraining creativity, autonomy, and user agency. The database search covered ACM Digital Library, Google Scholar, IEEE Xplore, Scopus, SpringerLink, and Web of Science, and was complemented by two focused backward and forward snowballing iterations. From 623 database records, the final synthesis includes 27 primary studies. The results show that direct literature combining cybersecurity, privacy, and Co-Creative Robotics remains limited, but evidence from creative HRI, social-robot privacy, cyber-physical security, privacy-preserving interaction design, security modeling, and robot ethics supports a conditional answer. Integration is feasible when security and privacy mechanisms are adaptive, explainable, participatory, context-sensitive, and lifecycle-aware. However, the evidence on transparency-oriented privacy mechanisms is mixed: improvements in awareness or acceptance do not consistently translate into reduced disclosure or greater perceived safety. Rigid controls may constrain creative exploration, whereas well-designed controls can support trust, accountable autonomy, safe embodiment, privacy-aware interaction, provenance, and agency-preserving creativity. The review proposes a conceptual lifecycle-oriented research agenda for secure and privacy-aware Co-Creative Robotics. Full article

The deployment of large language models (LLMs) in real-world applications introduces a compounding security problem: detecting adversarial inputs such as prompt injection and jailbreak-driven data leakage while simultaneously preventing the detection mechanism itself from becoming a source of data exposure. Existing approaches address either detection effectiveness or privacy preservation, but rarely both in a unified, deployable architecture. This paper proposes and evaluates a privacy-preserving hybrid middleware architecture that enforces a local trust boundary as its primary design constraint. The architecture combines deterministic rule-based screening, a fine-tuned small language model (SLM) operating entirely within the local processing environment, and a sensitivity-aware routing mechanism that invokes external LLM reasoning only for prompts all local components have assessed as non-sensitive. Evaluation on a 120-prompt benchmark spanning benign, jailbreak, and sensitive categories (including 20 hard negatives constructed to be lexically adjacent to genuine secrets) shows that the routed architecture attains 95.83% accuracy with complete recall, retaining 95% of sensitive prompts within the local boundary, at the cost of a 12.5% false-positive rate. Comparison against two published detectors reveals a systematic asymmetry: an injection-specific classifier reaches 82.5% recall on jailbreak prompts but 25% on sensitive ones, while a content-safety model inverts that profile, confirming empirically that the two risks are addressed separately by current tooling. The framework is model-agnostic, requires no retraining of the underlying LLM, and is compatible with black-box API deployments. The evaluation dataset and fine-tuned model are released publicly. Full article

Background: Global food supply chains have become increasingly complex, sourcing ingredients from multiple countries and intermediaries, creating opportunities for fraud, adulteration, and mislabeling that may compromise consumer safety and market confidence. Digital traceability technologies have been suggested as potential countermeasures, but there is little concrete evidence of their impact in practice. This research presents an assessment of the maturity and effectiveness of these technologies, identifies implementation barriers and security/privacy concerns, and maps research gaps/future directions. Methods: A scoping review of 64 studies from 2023 to 2026 with data extracted from the Scopus and IEEE databases was carried out according to the PRISMA-ScR guidelines and a structured pre-specified data extraction framework. Results: The field is empirically immature, with none of the reviewed solutions offering a provably correct, adversarially tested solution to the oracle problem. There is a lack of alignment between on-chain immutability and GDPR right to erasure and an unequal burden of implementation costs imposed on smallholder producers. Conclusions: A gradual implementation of traceability regulations, along with cost-of-ownership models and harmonized certification measures that do not disadvantage smaller producers are proposed. Finally, field trials, adversarial testing and reporting results in a standardized format, capturing detection performance and implementation costs, are essential. Full article

The adoption of federated learning (FL) has been on the rise in recent years due to the decentralized approach to data handling. Vertical federated learning is a type of FL that allows different parties to train shared models on complementary feature spaces without the direct exchange of data. However, the gradients these parties exchange can inadvertently carry sensitive information. Adversaries exploit this leakage to mount label inference attacks (LIAs) and adversarial attacks. To curb this, defense mechanisms have been deployed, but most of them either trade robustness for privacy and model utility or vice versa. This study addresses this gap by introducing an improved defense mechanism that combines adversarial training (to harden the model against adversarial perturbations) and differential-privacy-style noise injection (aimed at restoring the label privacy weakened by adversarial training) to collectively enhance the robustness of the existing KD$k$ defense mechanism with marginal model utility trade-off. Instead of relying on heavy encryption or post-processing techniques, it builds privacy directly into the learning dynamics of the model. It was evaluated using five publicly available datasets spanning three data modalities with the proposed mechanism achieving competitive near-baseline accuracy while significantly reducing label-inference success. Under FGSM-based adversarial evaluation, the robustness gap of this mechanism was found to be approximately 1% compared to the 36% robustness gap of the existing KD$k$ mechanism. The Privacy Leakage Index (PLI) reached 81.32%, 96.08%, 82.41%, 86.68% and 73.88% for CIFAR-10, CIFAR-100, CINIC-10, Yahoo! Answers and Criteo datasets, respectively. The results suggest that robustness and privacy security objectives can coexist to secure VFL with minimal effect on model accuracy. Full article

Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains, where poisoning attacks can corrupt training data, manipulate model updates, or implant covert backdoors. This survey examines poisoning attacks in federated learning (FL), using centralized learning as a baseline to explain how distributed data, client heterogeneity, privacy-preserving aggregation, and untrusted coordination expand the threat surface. It positions prior surveys and synthesizes representative primary studies through an accountability-oriented lens focused on attribution, audit evidence, traceability, and forensic readiness. The review compares major attack classes, including data poisoning, model poisoning, backdoor insertion, server-side manipulation, Sybil behavior, collusion, and multi-round poisoning. It also evaluates countermeasures such as Byzantine-robust aggregation, anomaly detection, validation-based filtering, malicious-secure aggregation, authenticated update handling, provenance mechanisms, ledger-based evidence, and verifiable aggregation protocols. The analysis shows that robustness alone is insufficient for trustworthy FL unless defenses also preserve evidence that supports independent verification, post-incident reconstruction, and governance review. Persistent gaps remain in causal forensic attribution, privacy-preserving evidence governance, malicious-server threat modeling, scalable verifiability tooling, recovery after poisoning, and deployment-ready benchmarks. The survey concludes that accountable FL should be designed as an evidence-producing system, not merely as a privacy-preserving or attack-resistant training architecture, especially for regulated, cross-silo, and high-risk real-world deployments. Full article

Sexually transmitted infections (STIs) remain a major global public health challenge, while stigma, privacy concerns, and barriers to healthcare access continue to delay diagnosis and treatment. This narrative review summarizes the current evidence on the use of artificial intelligence (AI) to support STI self-assessment and digital sexual healthcare while critically discussing its current applications, challenges, and limitations, based on a PubMed literature search. Existing studies demonstrate the potential of machine-learning algorithms for individualized HIV/STI risk prediction, symptom-based assessment, automated evaluation of genital lesions, and differentiation of sexually transmitted from non-sexually transmitted conditions, with reported diagnostic performance ranging from AUCs of approximately 0.75–0.95 for symptom assessment models up to 0.893 for multimodal image-based lesion classification and validation accuracies of 94.4% for real-world image analysis platforms. Advances in computer vision and radiomics further highlight the ability of image-based AI systems to identify diagnostically relevant lesion characteristics while improving model interpretability. In parallel, generative AI chatbots are increasingly being explored as tools for sexual health education, personalized risk assessment, behavioural support, triage, and linkage to care. These technologies also influence psychological aspects of sexual health by providing private and accessible support, facilitating risk appraisal, and addressing anxiety associated with STI concerns. However, insufficient demographic diversity and the reliance on retrospective training datasets, privacy and data security concerns, limited prospective validation, and uncertainty regarding real-world clinical effectiveness remain important barriers to the widespread adoption of these technologies. To address some of these limitations, future developments are expected to focus on multimodal and explainable AI systems integrated within digital sexual health ecosystems, with clinicians remaining central to the validation, interpretation, and contextualization of AI-generated assessments and the delivery of patient-centred care. Full article

Image steganography is an information-hiding technique, aiming to achieve confidentiality and data privacy while transmitting the data in a digital environment. Over the last two decades, steganography has evolved from classical spatial domain embedding to intelligent and adaptive steganographic systems capable of balancing imperceptibility, embedding capacity, robustness and security. This paper presents a review by categorizing the existing techniques into spatial domain-based, transform domain-based, hybrid and adaptive intelligent techniques. The review follows the PRISMA approach to make the selection process transparent for the inclusion and exclusion of papers in the study. Initially, the reviews include the spatial domain-based methods focusing on higher embedding capacity and simple embedding strategy, followed by transform-domain based techniques, including discrete cosine transform, discrete wavelet transform, and other multi-resolution wavelet transforms aiming to enhance robustness and imperceptibility by embedding the data into frequency coefficients. This paper further explores the methods that combine these techniques with other recent trends to develop adaptive and hybrid techniques. These techniques mainly integrate chaotic theory to enhance the security of secret data before embedding and optimization algorithms such as genetic algorithm, particle swarm optimization, Firefly, etc., for adaptive embedding to achieve an improved tradeoff. Finally, intelligent and adaptive techniques based on deep learning models such as convolutional neural networks, autoencoders, and generative adversarial networks are examined, highlighting their ability to learn intelligent embedding strategies and resist modern steganalysis. A comparative analysis is presented, including the technique, strengths, and limitations, together with the discussion of performance evaluation metrics and vulnerability analysis under image processing attacks. The review highlights the current trends and outlines the future direction to develop next-generation secure image steganographic systems. Full article

The integration of large-scale distributed energy resources (DERs) into distribution networks (DNs) brings challenges to the effective control of DNs. In traditional approaches, mathematical or reinforcement learning (RL)-based solution algorithms are commonly used. However, the exponential increase in the number of DERs reduces the effectiveness of these strategies. Mathematical methods struggle to cope with the dynamic uncertainty caused by the high penetration of renewable energy, while RL algorithms relying on global data training may violate multi-agent privacy protocols. This paper proposes a DNs cooperative optimization method based on resource aggregation and RL. To reduce optimization dimensionality and ensure the privacy of resource data, a dynamic aggregation strategy is employed to aggregate a large number of distributed energy resources into aggregated entities, and the adjustable active–reactive power boundaries of each aggregated entity are derived. To fully exploit the regulation capability of DNs, data centers (DCs), as novel devices, are considered as flexible loads. To improve the convergence speed of model training and decision-making accuracy, evolution strategies (ES) and prioritized experience replay (PER) are integrated into the Soft Actor-Critic (SAC) algorithm, respectively. The proposed method is validated on the IEEE 33-bus and IEEE 123-bus systems. The results demonstrate the effectiveness and superiority of the proposed method in ensuring the secure operation of DNs. Full article

Background: This study explores physicians’ perceptions and satisfaction with Electronic Medical Record (EMR) systems in resource-limited healthcare settings, addressing a critical gap in research. It identifies key factors essential for optimizing EMR adoption and enhancing healthcare delivery. Methods: This study employed a facility-based mixed-method cross-sectional study comprising a quantitative survey of 249 physicians at St. Paul’s Hospital Millennium Medical College (SPHMMC), sampled through stratified random sampling techniques, with thematic analysis of semi-structured interviews of eight physicians, selected using criterion and stratified purposive sampling techniques. Quantitative data was analyzed using both binary and multivariable logistic regression, and qualitative data from semi-structured interviews was analyzed using thematic analysis. Results: The study reveals that 91% of physicians experience workflow disruptions due to EMR system use. Despite this, physicians were satisfied with efficiency gains associated with EMR systems, with 65.8% noticing improvements in their efficiency and 50.6% reporting reduced workloads. 78.7% of physicians expressed satisfaction with workflow integration. EMR communication tools were rated positively, with 92.0% satisfied with integration. Overall, 79.5% of St. Paul’s Hospital Millennium Medical College (SPHMMC) physicians are satisfied with the implemented EMR system, with factors such as ease of use, integration, confidence in navigation, sufficient technical support, and perceived effectiveness in facilitating patient care across departments affecting satisfaction. The qualitative study also highlighted the following themes: a disconnect between system functionality and resource availability, usability and functionality gaps affecting workflow, inadequate training and support, data security and privacy concerns, and mixed perceptions of the EMR system’s impact on patient care benefits and challenges. Conclusions: The study shows that while the EMR system at SPHMMC has a mixed perception among physicians, it has generally satisfied them, and this supports a multifaceted approach to enhance physician satisfaction and optimize EMR utilization at SPHMMC. This includes enhancing system usability, providing comprehensive training, ensuring readily available technical support, improving workflow integration, and strengthening data security measures. Full article

Biometric authentication systems are increasingly deployed in critical security applications, yet the irreplaceable nature of biometric traits poses fundamental risks when templates are compromised. Unlike passwords or tokens, biometric data cannot be reissued, making template protection a paramount concern for preserving both security and privacy. This paper presents a novel multilayer framework for biometric template protection that integrates cancellability directly into the feature extraction stage, ensuring non-invertible and revocable templates while maintaining high recognition accuracy. The proposed method employs chaotic projection of Binarized Statistical Image Features (BSIF) filter banks, optimized through Particle Swarm Optimization (PSO), to generate discriminative yet irreversible biometric templates. To strengthen security against statistical and cryptanalytic attacks, dual-layer scrambling and diffusion processes driven by chaotic maps eliminate spatial correlations and produce uniform intensity distributions. Furthermore, Random Grid Visual Cryptography (RGVC) divides the encrypted template into two shares stored in separate databases, ensuring that the compromise of a single repository reveals no biometric information. Extensive experiments conducted on the PolyU multispectral palmprint database demonstrate exceptional authentication performance, achieving Equal Error Rate (EER) values as low as 0.0520% after applying the proposed protection framework, under optimal configurations. Comprehensive empirical security analysis demonstrates favorable statistical security characteristics, including near-zero pixel correlation, near-uniform intensity distributions, high entropy values approaching the theoretical maximum of 8 bits, favorable NPCR and UACI values, and high sensitivity to key variations under the considered experimental settings. The proposed framework satisfies the essential requirements of cancellable biometrics, including diversity, revocability, and non-invertibility, while providing a privacy-preserving biometric template protection approach. Full article

Artificial intelligence (AI) tools are being used in pharmacy practice in a variety of ways, such as enhancing the safety and efficiency of dispensing, compounding medications and helping pharmacists identify drug–drug interactions. The further development and use of these innovative technologies will be necessary to ensure patients can continue to access high-quality care amidst a growing health human resource crisis. However, in the field of pharmacy practice, little is known about actual or potential risks these tools pose to patients. A scoping review was conducted to map these risks. A database search of Ovid Medline, Ovid Embase, Ebsco CINAHL, and Web of Science, and a grey literature search were conducted. Three major potential risks were described in the literature: inaccuracies associated with AI outputs, privacy and data security concerns, and risks associated with algorithmic bias. Despite these potential risks, there is still a large gap in the literature regarding the study of risks of AI in pharmacy practice. While characterizing all risks associated with this rapidly changing technology may be impossible, further exploration of risk, perhaps using novel approaches to understanding risk itself, is warranted if these technologies are to be adopted responsibly and used safely. Full article

Smart cities (SCs) use the Internet of Things (IoT) to collect and process data to communicate with their infrastructure and assets in real time. A great deal of techniques, such as encryption protocols, Random Forest-based AI-driven threat detection, and blockchain architectures, have been developed to address cybersecurity challenges in smart cities (SCs). These techniques, however, have limitations such as their scalability, high computational expenses, and energy inefficiency. Therefore, in this study, to overcome these challenges, we propose a blockchain-based infrastructure called BlockSafeNet. This uses artificial intelligence, big data, and blockchain to enhance cybersecurity in SCs. The effectiveness of the proposed BlockSafeNet framework was evaluated using responsiveness, computational time, encryption quality score, detection rate, false positive rate, latency, throughput, and energy consumption as the primary cybersecurity performance metrics. These metrics were selected to assess communication efficiency, threat detection capability, privacy preservation, scalability, and overall security performance within smart-city IoT environments. To ensure secure data transactions, robust threat detection, and efficient communication. The system’s high calculation speed and detection rate show potential for managing sensitive maternal health data collected by IoT devices. The platform also shows how IoT may be used by healthcare services to monitor public health in real time, allowing hospitals, emergency services, and public health agencies to securely share data. This aids in resource optimization, improving service delivery, and preserving data privacy and trust in SCs. Data was obtained from the UCI Machine Learning Repository on Kaggle to validate the developed framework. By evaluating the effectiveness of BlockSafeNet in tackling cybersecurity challenges, we establish its practical relevance and usability in SCs. The proposed BlockSafeNet framework achieved a responsiveness of 24 s, an encryption quality score of 0.89, computational time of 85 s, and a detection rate of 91%, demonstrating significant improvements in secure IoT communication, privacy preservation, and AI-driven cyber threat detection within smart city infrastructures. shows that SC IoT security has significantly improved through the adoption of new data protection methods and better measures of security, providing a positive impact on the SC ecosystem. Full article

Outsourcing Internet-of-Things (IoT) data and computation to cloud and fog infrastructure exposes both the data and the access-control process to integrity, confidentiality, and privacy risks. Attribute-based encryption (ABE) provides fine-grained access control but, as deployed today, suffers from single-authority bottlenecks, expensive policy updates, weak auditability, and exposure to secret-key leakage, classical primitives are additionally threatened by future quantum adversaries. This paper does not propose a new cryptographic scheme. Instead, it contributes a conceptual reference architecture that systematizes how a set of existing, standardized primitives can be composed into a single access-control framework for IoT outsourcing, and it makes the resulting design precise enough to reason about. Concretely, we (i) define a system model and a threat model covering passive, active, colluding, bounded-leakage, and harvest-now-decrypt-later quantum adversaries; (ii) instantiate each layer with a named construction decentralized multi-authority ABE, attribute-based proxy re-encryption for policy updates, a bounded leakage resilient key model, ASCON lightweight AEAD, and ML-KEM/ML-DSA post-quantum primitives, together with a permissioned, on-chain digest/off-chain payload logging layer; (iii) specify the end-to-end data flow and module interfaces; and (iv) give a goal-by-goal security rationale and an analytical evaluation based only on standardized parameter sizes and asymptotic complexity. We are explicit about what is inherited from prior work, what remains to be proven for the composed system, and that a measured prototype evaluation remains future work. The intended value of this paper is to provide a clear, composable, and honestly scoped design that subsequent implementation studies can build upon. Full article