The increasing adoption of Digital Twins (DT) driven by the Internet of Things (IoT) in critical domains such as healthcare, smart energy, and mobility introduces unprecedented privacy risks due to continuous data collection, contextual sensitivity, and user traceability. We propose PRivacy in DT with minimum privacy budget ( \(\varepsilon\) ), PRiD \(\varepsilon\) , a context- and pattern-aware, genetically optimized adaptive Differential Privacy (DP) model to secure DT through a modular four-layer architecture. PRiD \(\varepsilon\) combines contextual sensitivity estimation, domain-specific heuristics, and genetic noise injection to achieve adaptive per-pattern DP guarantees. It integrates Federated Learning (FL), dynamically tuning \(\varepsilon\) across local nodes based on sensitivity feedback and evolving model requirements. A privacy-sensitive access control mechanism regulates query responses by role, budget, and pattern-level risk. Evaluations across healthcare, smart energy, and mobility demonstrate high utility ( \(>\) 95%) at low \(\varepsilon\in[0.1,0.35]\) , and strong resilience against reconstruction, inference, and \(\varepsilon\) -variation exploitation attacks. PRiD \(\varepsilon\) supports scalable, privacy-preserving DT modeling, with theoretical analysis and empirical benchmarking indicating an overall worst-case complexity of \(\mathcal{O}(n\log n)\) under the proposed pipeline.

In an increasingly digital and interconnected world, the need for robust network intrusion detection systems is crucial to ensure cybersecurity. This article presents a novel approach to network intrusion detection that integrates both traditional machine learning methods and advanced reinforcement learning techniques to enhance detection capabilities and accuracy. The proposed system uses Proximal Policy Optimization, a reinforcement learning algorithm, to dynamically adjust ensemble weights, thereby optimizing the contributions of base learners, such as Random Forest and CatBoost. Additionally, a Multi-layer Perceptron-based meta-learner is employed to refine the predictions, leading to an overall improvement in detection performance. The model was evaluated on five diverse datasets, including NSL-KDD, CICIDS, TON IoT, DDoS, and UNSW-NB15, achieving an average accuracy of 97.16%, and an average precision, recall, and F1-score of 97% across all datasets. The proposed work is compared with the existing state-of-the-art detection methods demonstrating its better performance in detecting both known and novel attack types. Furthermore, the integration of reinforcement learning allowed for dynamic and context-sensitive decision-making, enabling the system to handle complex attack patterns that traditional models struggle with. The training and validation results across all datasets showed rapid convergence and minimal overfitting, further supporting the model’s robustness.

This paper proposes a novel agglomerated privacy-preservation model integrated with data mining and evolutionary Genetic Algorithm (GA). Privacy-pReservIng with Minimum Epsilon (PRIM$\epsilon $) delivers minimum privacy budget ($\epsilon $) value to protect personal or sensitive data during data mining and publication. In this work, the proposed Pattern identification in the Locale of Users with Mining (PLUM) algorithm, identifies frequent patterns from dataset containing users’ sensitive data.$\epsilon $-allocation by Differential Privacy (DP) is achieved in PRIM$\epsilon $with GA$_{\textbf {PRIM$\epsilon $}}$, yielding a quantitative measure of privacy loss ($\epsilon $) ranging from 0.0001 to 0.045. The proposed model maintains the trade-off between privacy and data utility with an average relative error of 0.109 on numerical data and an Earth Mover’s Distance (EMD) metric in the range between [0.2,1.3] on textual data. PRIM$\epsilon $model is verified with Probabilistic Computational Tree Logic (PCTL) and proved to accept DP data only when$\epsilon \le 0.5$. The work demonstrated resilience of model against background knowledge, membership inference, reconstruction, and privacy budget attack. PRIM$\epsilon $is compared with existing techniques on DP and is found to be linearly scalable with worst time complexity of$\mathcal {O}$(n log n).