Newest papers

AdaFedXplain: Adaptive Federated Learning with Explainable AI for Ransomware Detection

Md. Emran Biswas, Md. Delowar Hossain, Mst. Tanbin Yasmin Tanny, Muhammad Aminur Rahaman, Md Al Amin, Tangina Sultana · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25318 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los ataques de los sistemas latentes con el uso de ransomware se han desarrollado en campañas complejas de datos multifásicas que dirigen a infraestructuras vitales, lo que resulta en daños anuales de miles de millones de dólares. Las técnicas de detección convencionales son ineficaces contra las variaciones del día cero, y los problemas de privacidad son planteados por algoritmos de aprendizaje de máquina centralizados. El aprendizaje federado permite la formación de modelos cooperativos sin compartir datos, pero los enfoques actuales de FL sufren de problemas de explicabilidad, alto coste de comunicación y heterogeneidad de datos no IID. En este estudio, presentamos AdaFedXplain, un paradigma de aprendizaje federado adaptativo basado en IA interpretable para la detección de ransomware. Nuestro enfoque incluye la complejidad

Machine translation (Meta M2M100); the English original follows.

Abstract

Attacks using ransomware have developed into complex multiphase campaigns that target vital infrastructure, resulting in annual damages of billions of dollars. Conventional detection techniques are ineffective against zero-day variations, and privacy issues are raised by centralized machine learning algorithms. Federated learning allows for cooperative model training without data sharing, however current FL approaches suffer from explainability issues, high communication cost, and non-IID data heterogeneity. In this study, we present AdaFedXplain, an explainable AI-based adaptive federated learning system for ransomware detection. Our approach includes progressive XGBoost complexity to avoid overfitting, a decaying learning rate schedule for stable convergence, and dynamic client grading based on ransomware prevalence and data sufficiency. Using 62,485 real-world ransomware samples from four OS-based non-IID clients, we compare AdaFedXplain against FedAvg, FedProx, and SCAFFOLD. According to experimental data, AdaFedXplain outperforms all baselines with 99.59% detection accuracy and 99.64% F1-score while cutting energy usage by 75%, latency by 65%, and communication overhead by 75%. The ablation investigation demonstrates that every element enhances performance. Security analysts can use SHAP explainability to identify important PE header characteristics that influence detection decisions. Our system provides a collaborative ransomware detection solution that is efficient and interpretable, while reducing privacy risks through federated learnings data-local training paradigm.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Ransomware, Computer science, Federated learning, Overhead (engineering), Computer security, Supervised learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange