Federated Analytics for Privacy-Preserving Edge Computing

Federated Learning in Distributed Cloud Systems: Enhancing Privacy and Scalability for Machine Learning in Edge Computing

This paper investigates the implementation of FL in distributed cloud systems, highlighting its role in preserving data privacy and improving scalability, and analyzes various FL algorithms, such as Federated Averaging (FedAvg), assessing their effectiveness in edge computing contexts.

A Survey on Privacy-Preserving Techniques for Cloud Data Processing Using Homomorphic Encryption and Federated Learning

This paper presents a structured review of privacy-preserving data processing techniques for cloud environments built on HE and FL, individually and in hybrid combination, and identifies promising directions for future research.

Doppio : Communication-Efficient and Secure Multi-Party Shuffle Differential Privacy

Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata

Clustered Federated Learning (CFL) addresses data heterogeneity in federated settings by grouping clients with similar data distributions to enable effective training. Existing methods face a trade-off between privacy preservation, communication cost, and computational efficiency. We formalize this as the CFL trilemma, according to which improving two of these dimensions comes at the expense of the third. A prominent paradigm relies on metadata (i.e., low-dimensional representations of client datasets shared with the server) to enable communication- and computation-efficient clustering. However, such approaches are not compatible with standard FL privacy-preserving mechanisms. To address this limitation, we propose FLAMECHE, which reformulates metadata-based CFL as a distributed Expectation-Maximization (EM) procedure, restricting server updates to additive operations while preserving efficiency. This design enables compatibility with practical secure FL schemes. We conducted extensive experiments on multiple datasets under various heterogeneous scenarios. Results show that FLAMECHE improves the effectiveness of client models. It enables encryption-compatible metadata-based clustering, enhancing its positioning within the CFL trilemma.

Intelligent Privacy: Preserving Split Learning Framework for Decentralisation Data Deduplication in Edge Environment

: Driven by the emergence of edge computing and its ever-growing need for more efficient systems to manage information of ever-increasing volume, privacy-preserving digital fingerprint and distributed learning have received far greater importance in recent years decade contributions from this author When by advertising ``split '', a novel technique has emerged that retains data deduplication and decentralization, but also solves issues such as privacy resource usage and scalability. Different from current literature that largely sacrifices de-duplication accuracy or improved copy finding as a result of focusing exclusively on either the problem of de-duplication, machine learning, ours approach in developing high-slash, splits with splits come together to do intelligent data management and a reasonable measure of privacy.This paper uses the existing methods of fine-grained deduplication, resource allocation, and blockchain-based decentralized system to extend this idea, providing a safe and efficient solution for edge computing. Dependencies testing implies that the adaptability and efficiency of the framework are validated by experimental simulations, and the results have demonstrated its effectiveness in eliminating redundant data, as well as improving the performance of edge-located machine learning systems.

Quantifying and Preventing AI-Aware Privacy Leakage in Large-Scale Data Ecosystems: A Systematic Review

Now, AI runs on cloud platforms, edge systems with federated settings, and in large language model (LLM) pipelines or data-sharing services, creating even wider privacy leakage paths beyond classical database disclosure. This paper offers a systematic, structured review of the literature on a curated, cost-effective reference corpus for quantifying and preventing privacy leakage in AI-enabled data ecosystems. The review ties together four strands of research that are often treated separately. Firstly, the privacy risk throughout the AI life cycle. Secondly, the measurement of the quantitative leakage. Thirdly, architectures of the privacy-preserving models, and finally, operational governance for real-world deployment. Our analysis demonstrates that state-of-the-art approaches are moving from static mechanisms based on anonymization to metric-aware protections, including information-theoretic leakage scores, cumulative differential privacy accounting, personalized privacy budgets, and benchmark-driven attack evaluation. In parallel, prevention methods are evolving beyond single homomorphic noise injection and are becoming multi-layered defenses that combine differential privacy, federated learning, weight quantization, synthetic data generation, policy-driven automation, and LLM controls. The review uncovers four itchy gaps: fractured assessment metrics, shaky privacy-utility trade-offs, flimsy integration of technological controls and compliance processes, and low cross-context validation across cloud-based computing, edge computing (data processing at or near the source), federated learning (distributed machine-learning methods), and generative AI systems. The paper concludes by outlining a unified research agenda to build AI-aware, quantifiable, and usable privacy protection stacks.