Aug 2026· International Conference on Machine Vision and Deep Learning· Vol 14326, pp. 143261R - 143261R-8· 0 citations· 16 references
Engineering
TL;DR
The results demonstrate that federated learning is a scalable and effective method that can achieve privacy compliance in e-commerce analytics within data-restricted environments, and it lays a solid foundation for secure distributed business intelligence.
Abstract
A federated learning-based privacy-preserving prediction model is proposed for large-scale e-commerce user behavior analytics. The framework enables multiple e-commerce platforms to collaboratively train predictive models without transmitting raw user data, addressing the dual demand for high accuracy and robust data privacy. The main components of the system include secure aggregation protocols, which protect local model updates from exposure; differential privacy mechanisms, which inject controlled noise during distributed training to obscure individual user contributions. The system architecture supports asynchronous client participation, dynamic scaling, and heterogeneous feature engineering across organizational boundaries, which facilitates deployment in real-world e-commerce environments. Experimental validation conducted in multi-isolated environments shows that the federated method is as accurate as centralized models while significantly reducing privacy leakage. In addition, the model maintains a high recall rate in rare event scenarios and is able to balance privacy budget and prediction performance. Empirical risk assessment indicates that even with an increase in the number of participants or data diversity, privacy protection is significantly enhanced while maintaining analytical utility. The results demonstrate that federated learning is a scalable and effective method that can achieve privacy compliance in e-commerce analytics within data-restricted environments, and it lays a solid foundation for secure distributed business intelligence.
A federated deep learning framework that systematically integrates adaptive privacy noise mechanisms and trust-weighted aggregation within a distributed architecture that ensures the protection of sensitive data during collaborative analysis through precise differential privacy control and advanced neural network models is presented.
Predictive customer behavioral modeling has long assumed centralized access to raw interaction data an assumption that regulatory frameworks, competitive constraints, and cross-organizational data governance requirements render increasingly untenable in contemporary enterprise environments. Federated learning offers a principled alternative, enabling collaborative model training across distributed data holders without centralizing behavioral records. However, standard federated learning frameworks were designed for device-level settings whose structural properties differ substantially from those of customer behavioral data: interaction sequences are longer and sparser, distributions across organizational participants are more heterogeneous, and privacy sensitivities are more legally consequential. The paper proposes a systematic analysis framework for investigating five structural aspects, which need behavioral-specific adjustment beyond regular federated learning approaches in the following contexts: feature engineering with data locality; communication efficiency during distributed behavioral model training; differential privacy in behavioral prediction pipelines; non-IID distribution of behaviors in cross-silo federations; and secure aggregation with Byzantine resilience. For each dimension, the article identifies the specific failure modes that arise when canonical methods are applied without adaptation and provides practitioner-oriented design guidance. The analysis further proposes a deployment-prioritized research agenda whose sequencing is determined by the severity with which unresolved challenges block production deployment. The framework contributes both a diagnostic lens for organizations evaluating federated behavioral intelligence adoption and a structured research roadmap for the methods community.
Kali Prasad Chiruvelli· International Journal of Com...· 0 citations
Traditional federated learning has challenges such as slow model convergence, lagging situational awareness, and risk of gradient privacy leakage in cyber threat collaborative analysis capability. This study proposes a federated learning privacy-preserving collaboration model based on threat intelligence drive and hierarchical aggregation. The model optimizes participating nodes through a dynamic client selection mechanism, uses a hierarchical aggregation strategy to balance the learning of basic features and advanced threat patterns, and introduces an adaptive differential privacy mechanism to strengthen gradient protection. The experiment is based on the CIC-IDS-2018 public dataset, which covers various types of attacks in real network environments, with a data volume of approximately 5 million pieces. It is divided into 50 clients in a non-independent and identically distributed manner to simulate cross organizational collaboration scenarios. In the threat detection task, the model designed by the research institute achieved an accuracy of 91.8% and an F1 Score of 89.8% compared to baseline models such as FedAvg, FedProx, and DP FedAvg. All indicators were superior to the comparison model. In addition, in the advanced persistent threat attack scenario, the attack chain detection rate increased to 95.6%, and the average detection time was shortened to 2.8 hours. In terms of privacy protection, the Rényi privacy loss was only 2.89 with a budget of ε=3.0. The proposed model effectively improves the efficiency and timeliness of collaborative detection of cross-organizational threats while ensuring data privacy and provides a feasible solution for building a safe and reliable collaborative defense system. It should be pointed out that while improving detection performance, the model introduces additional communication overhead caused by hierarchical aggregation and dynamic selection mechanisms. The average communication traffic in the experiment was about 13.8 GB. As the number of clients expands to a larger scale, the computational load and scheduling complexity of the coordination layer will further increase. In addition, although the non-independent and identically distributed data partitioning used in the experiment can simulate real heterogeneous scenarios, the convergence efficiency of the model under extreme distributions still needs further verification. The above limitations will be optimized in future work by introducing asynchronous aggregation and lightweight communication protocols.
This study proposes a Federated Predictive Learning with Privacy-Aware Model Aggregation (FPL-PAMA) framework, suitable for applications including healthcare, IoT, smart manufacturing, transportation, and financial fraud detection, providing a secure and scalable solution for next-generation distributed intelligent systems.
Mahabala H. N., Seshagiri N· International Journal of Mac...· 0 citations
Federated learning is a decentralised machine-learning approach in which several clients jointly build a shared model without moving their raw data to one location. Rising concerns around privacy, tightening regulation, and restrictions on how data may be owned or shared have made this approach increasingly attractive in practice. Although federated learning lowers privacy exposure relative to centralised training, deploying it in practice is complicated by clients whose data are unevenly distributed and non-identically distributed, by clients that participate inconsistently, and by training that can converge unpredictably. To obtain global models that train reliably and consistently even when client data are heterogeneous, this work puts forward a federated learning system built around privacy preservation. The design follows a client–server pattern in which a coordinating server aggregates updates from local models using weights that account for imbalance among participants. The behaviour of the resulting system is examined methodically across several data-distribution regimes — IID, mildly non-IID, and severely non-IID. The experiments show that the framework converges reliably and delivers predictive accuracy that holds up well, especially in the more difficult non-IID cases. Compared with conventional federated learning baselines, the approach shows greater robustness and steadier performance across successive training rounds. Because it is simple to implement, repeatable, and built with real deployment in mind, the architecture suits privacy-sensitive, decentralised use cases such as distributed intelligent systems, industrial monitoring, and healthcare analytics.
Shyam Patel, S. Khan· 2026 International Conferenc...· 0 citations
This project proposes a privacy-preserving framework for location-based services, incorporating federated analytics, secure computation and mobility intelligence for customized next-location prediction and recommendation of points-of-interest. The proposed system is based on the Foursquare NYC check-in data set of user-wise location traces, venue categories, geographic coordinates and timestamps. The whole dataset is split by user identity to simulate federated clients and all user check-in logs are not stored at a central server. Clients train an LSTM-based sequence model to learn temporal mobility behavior from their check-in patterns locally. Gaussian noise is applied using a differential privacy layer prior to the sharing of model updates, to minimize the likelihood of revealing information about the location of the user. The noisy local updates are then aggregated at the Flask server using the FedAvg algorithm, which leads to an aggregated mobility model without noise. In addition to next-location prediction, the system uses matrix factorization to produce top 5 recommendations and DBSCAN clustering to detect spatial hotspots based on spatial patterns. The frontend is created with HTML, CSS, JavaScript and Leaflet.js and presents recommended venues, predicted latitude/longitude, hotspot heatmap and an epsilon-based privacy budget meter. The novelty of the work is that the location prediction, POI recommendation, hotspot detection, federated aggregation, and differential privacy are all integrated into a unified location-based service architecture. This not only facilitates beneficial mobility analytics but also minimises the central exposure of sensitive GPS traces and enhances the privacy awareness of location-based recommendation systems.
Mr. M. Amareswara Kumar, M. Bhavana, Pg Student et al.· 2026 6th International Confe...· 0 citations