Federated Learning (FL) is susceptible to adversarial attacks, such as Label Flipping (LF) and Backdoor, where malicious clients manipulate the updates of their local model to reduce the global model’s performance. Traditional FL relies on a centralised aggregator, which must be trusted, creating a single point of failure. This centralization not only increases computational cost but also introduces scalability challenges. To address these issues, we propose a Blockchain (BC) based FL framework that decentralises the aggregation process and incorporates an enhanced Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method to identify and remove malicious updates without ignoring minor groups. Our approach eliminates the need for a centralised aggregator by leveraging BC’s smart contracts to aggregate the global model. Simultaneously, Enhanced DBSCAN identifies malicious updates in the parameter space, effectively mitigating adversarial influence while preserving privacy. We evaluate both of our framework and the traditional FL under LF red and Backdoor attacks, experimental results demonstrate that our approach outperforms the traditional FL according to multiple metrics, including accuracy, loss, precision, recall, and F1-score. These findings emphasise the effectiveness of our BC-based decentralised aggregation combined with enhanced DBSCAN technique in improving the robustness and security of FL systems.

Generalized stochastic Petri nets (GSPNs) have been extended to several dynamic-structure formalisms providing suitable tools for the modeling and verification of reconfigurable discrete-event systems (R-DESs). However, analyzing the performance of large-complex R-DESs remains a big challenging issue. Indeed, dynamic-structure GSPNs still rely on old-fashioned techniques often causing the state-space explosion problem. In this article, we present a new technique for the quantitative analysis of a dynamic-structure formalism called reconfigurable GSPNs without computing the whole state space. This work describes new reconfiguration forms used to preserve desired quantitative properties of parts of interest after each reconfiguration. Therefore, it is only required to verify the examined properties at an initial configuration. The proposed technique is proven to effectively reduce the state space and shorten the computation time in such cases. Finally, some experimental results are provided to illustrate that, from a computational perspective, the developed approach outperforms the existing tools.

Nowadays, managers are looking for adequate strategies and advanced logistics management models in order to achieve their competitiveness and improve their overall performance. The current literature on supply network planning has not adequately incorporated sustainability factors, uncertainties, and the integration of various levels of planning (operational, tactical and strategic). In this paper, we address the integrated planning of logistics networks in an uncertain and sustainable environment. The problem is formulated as a two-stage stochastic programming which minimizes the logistics costs and evaluates a posteriori the CO2 emissions and the transport accident risk. This model is solved using the Sample Average Approximation (SAA) approach. Numerical experiments are performed using CPLEX to study the impact of different parameters on sustainability aspects.

Several variants of particle swarm optimization (PSO) have been created to identify various solutions to compli-cated optimization problems. Only a few PSO algorithms exist that can locate and monitor multiple optima in dynamically shifting search landscapes when dealing with dynamic optimization situations. These methods have yet to be thoroughly tested on a large number of dynamic optimization problems. In fact, because there are so many PSO algorithm modifications, it's simple to get stuck in a local optima. To address the aforementioned flaws, this work proposes and evaluates an enhanced version of the multiswarm particle swarm optimization technique (MsPSO) with numerous variations particle swarm optimization published in the literature. Standard tests and indicators provided in the specialized literature are used to verify the effectiveness of the suggested algorithm. Furthermore, on the CEC’ 13 test suite, comparison results between the extended heterogeneous multi swarm PSO algorithm (XMsPSO) and other nine popular PSO show that XMsPSO achieves a very optimistic performance for solving various kinds of problems, contributing to both higher solution accuracy.

This paper focuses on verification and validation (V&V) of a model dedicated to mode handling of flexible manufacturing systems. This model, specified using the synchronous formalism Safe State Machines, was proposed in our earlier work. The rigorous semantics that characterize such formalism enable to provide formal verification mechanisms ensuring determinism and dependability. A structured framework for verification and validation of a specification model is presented. The main properties being verified are proposed and illustrated through an example of a manufacturing production cell. The formal analysis tools integrated into the development environment Esterel Studio are used within the design process.