Poster: SCL-IDS – A Semi-Supervised Continual Learning Framework for Adaptive Intrusion Detection

As modern network infrastructures grow in complexity, intrusion detection systems (IDS) face increasing challenges in detecting emerging threats under non-stationary conditions. Real-world traffic is characterized by continual attack evolution, severe label scarcity, and imbalanced distributions. Traditional IDS approaches often fail to maintain accuracy over time due to catastrophic forgetting, while supervised methods demand costly manual annotations.