Poison-Proof AI: New Study Shows How to Keep IoT Intrusion Detectors Honest Under Attack
A massive 641-run study shows that trust-weighted federated learning can keep a tiny on-device IoT intrusion detector accurate under non-IID ...
A massive 641-run study shows that trust-weighted federated learning can keep a tiny on-device IoT intrusion detector accurate under non-IID ...
Researchers in India have developed a post-quantum attribute-based encryption scheme based on the Cyclic Learning With Errors problem that shrinks ...
Researchers have developed a feedback-guided framework that adapts decision thresholds instead of retraining classifiers, achieving near-equal accuracy with lower false ...
Researchers have developed a hybrid Grey Wolf Coot Optimization routing framework with dynamic physically unclonable functions that cuts IoT energy ...
A new federated learning framework called FedCAMP-IDS detects known and zero-day cyberattacks across heterogeneous IoT networks with up to 99.16 ...
Researchers in India report that a Bayesian-optimized decision tree detects black hole attacks in RPL-based IoT networks with 98.71% accuracy, ...
Researchers at Manipur University have developed EF²RB, an ensemble feature selection framework that boosts IoT intrusion detection accuracy to between ...
Researchers have developed an AI-driven trust and decision-making framework that uses software-defined networking and the Bat Algorithm to select secure, ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine