A review of intrusion detection systems argues signature-based tools miss novel attacks while anomaly-based ones trigger false alarms, and evaluation datasets are outdated.
A deep neural network beats classical machine learning at spotting network and host intrusions across six benchmark attack datasets, and the authors propose a scalable real-time monitoring framework.
A survey mapping how machine learning and deep learning are used to detect network intrusions, plus the datasets, limits, and open problems in the field.
A broad review of intrusion detection systems, mapping how they work today across cloud, IoT and industrial networks, and where AI and blockchain could take them next.
A recurrent neural network whose settings are tuned by a nature-inspired "fox" search algorithm detects network intrusions 4-15% more accurately than four competing deep learning models.
A lightweight LSTM-based system can spot attacks on a car's internal CAN network in near real time without the overhead of encryption.
A federated learning intrusion detector spots attacks on car networks with over 99% F1 score using just 1.11 MB of memory.
Connecting solar, wind and batteries to digital grids opens serious hacking routes, and current defenses lack real-time detection, cross-domain data protection and harmonized policy.
Turning just five consecutive network packets into an RGB image lets a lightweight intrusion detector spot attacks early with 99% accuracy.
A hybrid CNN + Bi-LSTM + attention model with transfer learning detects IoT cyberattacks across different networks with 96-98% accuracy, beating existing detectors.
Adding federated trust learning, quantum-resistant encryption, and reusable trust tokens to a vehicle authentication framework cut cross-domain authentication delay by 45%.
A federated CNN-Transformer model detects attacks on connected medical devices with ~99% accuracy across three datasets without pooling hospitals' raw data centrally.
A review of explainable-AI intrusion detection for IoT finds the field now chases lightweight, transparent, privacy-preserving designs — but rarely validates its explanations or reproduces results.
Software-only security testing misses how car cyberattacks physically behave; hardware- and vehicle-in-the-loop rigs plus AI detection are needed to realistically test and defend connected vehicles.
A new method lets federated IoT intrusion detectors erase a device's data influence almost as well as full retraining, but far faster.
A drone-assisted graph learning system spots coordinated DDoS attacks across EV charging networks with 97.7% accuracy, beating localized traffic-only detectors.
A hybrid Transformer-CNN trained with federated learning identifies users from mouse movements with 99.51% accuracy while keeping raw behavioral data on their own devices.
Combining ant-colony feature selection with a CNN-BiLSTM attention network detects cyberattacks on smart consumer-electronics networks more accurately than existing intrusion detection methods.
AI intrusion detection for industrial IoT scores well on benchmarks but still fails on generalization, explainability, adversarial attacks, and real-world edge deployment.
Pre-training intrusion detectors on big computer-network attack datasets, then fine-tuning on small IoT ones, beats training from scratch and compresses to run on edge devices.
A unified deep learning system, X-THREAT, spots rare and never-before-seen cyberattacks with 93-96% accuracy across three benchmarks while explaining its decisions.
HyperIDS combines hypergraph neural networks, quantum-inspired feature selection and a transformer ensemble to detect IoT cyberattacks with about 98.9% accuracy.
Combining supervised and unsupervised detectors in a weighted ensemble, plus a hash-chained audit log, flags network intrusions with 98.85% accuracy and tamper-evident records.
A combined deep-learning and blockchain system detects attacks in cloud-connected sensor networks and logs them tamper-evidently, beating LSTM and CNN-RNN baselines on two datasets.
Combining boosted decision trees and bagged random forests detects IoT botnet traffic more sensitively, and SHAP explains which network features drove each decision.
FedShield-IDS trains a CNN-LSTM intrusion detector across smart-home devices without sharing raw traffic, and uses SHAP to explain every alert.
Combining self-supervised learning, prototypical few-shot networks and continual learning detects new botnet attacks from very few samples, hitting 98.50% accuracy on CIC-IoT-2023.
A new intrusion detection system combines three machine learning models with an attention layer, SHAP explanations, and tamper-proof hashed logs to make attack alerts auditable.