An efficient cyber-attack detection and classification in IoT networks with high-dimensional feature set using Levenberg-Marquardt optimized feedforward neural network. [PDF]
PLoS OneKuang Q, Kuang X.
europepmc +1 more source
Advanced Science, Volume 13, Issue 7, 3 February 2026.This paper presents a programmable metasurface‐based Meta Key Distribution (MKD) system for secure, protocol‐independent key exchange in indoor wireless settings. By embedding entropy into the wireless channel, it enables lightweight, compatible cryptographic key generation.
Xinyu Li +7 more
wiley +1 more source
Two-Tier heuristic search for ransomware-as-a-service based cyberattack défense analysis using explainable Bayesian deep learning model. [PDF]
Sci RepAlmuflih AS.
europepmc +1 more source
Digital Agriculture: Past, Present, and Future
Advanced Intelligent Discovery, Volume 2, Issue 1, February 2026.Digital agriculture integrates Internet of Things, artificial intelligence, and blockchain to enhance efficiency and sustainability in farming. This review outlines its evolution, current applications, and future directions, highlighting both technological advances and key challenges for global implementation.
Xiaoding Wang +3 more
wiley +1 more source
Enhanced IoT threat detection using Graph-Regularized neural networks optimized by Sea-Lion algorithm. [PDF]
Sci RepSanthosh DT +5 more
europepmc +1 more source
Meta Reinforcement Learning for Automated Cyber Defence
Applied AI Letters, Volume 7, Issue 1, February 2026.ABSTRACT Reinforcement learning (RL) solutions have shown considerable promise for automating the defense of networks to cyber attacks. However, a limitation to their real world deployment is the sample efficiency and generalizability of RL agents. This means that even small changes to attack types require a new agent to be trained from scratch.
Andrew Thomas, Nick Tillyer
wiley +1 more source
Orchestrating machine learning models in a swarm architecture for IoT inline malware detection. [PDF]
Sci RepHanif M +5 more
europepmc +1 more source
Multi‐Agent Reinforcement Learning for Cyber Defence Transferability and Scalability
Applied AI Letters, Volume 7, Issue 1, February 2026.A method for using mutli‐agent reinforcement learning that allows for zero shot transfer across network setups. Diagrams show the local observation construction, training and agent mapping process. The results for novel 15 and 30 node networks show effective transfer and improved scaling performance. ABSTRACT Reinforcement learning (RL) has shown to be
Andrew Thomas +2 more
wiley +1 more source
AAPM working group on cybersecurity report 438: A white paper on cybersecurity management for business continuity in radiology and radiation therapy. [PDF]
J Appl Clin Med PhysSiochi RA +7 more
europepmc +1 more source