Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks
A study on lightweight machine learning models for IIoT intrusion detection found that they have limited generalization across different networks. The models rely heavily on coarse port-category features and are affected by imbalanced class distributions.
#adversarial-robustness#cross-network-generalization#industrial-internet-of-things#intrusion-detection#machine-learning
Read original ↗Sign in to upvoteSign in to save