Lightweight AI Intrusion Detection System Targets IoT and Medical Device Threats
Researchers report a lightweight, imbalance-aware intrusion detection system achieving up to 0.9998 accuracy on IoT and medical IoT benchmark datasets.
Researchers report a lightweight, imbalance-aware intrusion detection system achieving up to 0.9998 accuracy on IoT and medical IoT benchmark datasets.
A systematic review of 120 papers finds deep learning DDoS detectors excel in experiments but struggle in real-world cloud environments, ...
Researchers have built a federated, explainable deep learning framework that detects attacks on Internet of Medical Things devices with detection ...
A new simulation study presents GuardBox, a framework combining an LSTM autoencoder and random forest classifier to detect and attribute ...
A new framework called TinyRoute combines TinyML, reinforcement learning, and few-shot learning to achieve adaptive routing and zero-day attack detection ...
A four-tier wearable health monitoring framework combining multimodal deep learning, federated learning, differential privacy and blockchain auditability has reported strong ...
A mixed-method study combining a bibliometric review of 2,015 publications with interviews of 10 developers and 10 users finds that ...
A study combining Transformer, deep neural-network and recurrent models with adaptive weighting reported 95% accuracy and 96% recall when detecting ...
Researchers report that a hybrid model combining dynamic convolution, a Kolmogorov-Arnold network and a closed-form continuous-time neural network outperformed classical ...
A deployment-efficient CNN-LSTM framework with channel attention detects encrypted, imbalanced, and heterogeneous malicious traffic in real time on CPU-only hardware, ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine