Intrusion Detection System for Open Network Scenarios: A Known/Unknown Attack Detection Method Based on Inter-Class Relationships

Intrusion detection systems (IDS, software that monitors networks for unauthorized access attempts) trained on known attack data struggle to detect new, unknown attacks because they have rigid decision boundaries that don't adapt well. This research proposes a new method that uses virtual classes (imaginary attack categories placed between known attacks) and soft labels (flexible probability scores instead of strict categories) to better distinguish between known and unknown attacks, achieving significantly higher detection accuracy on standard network security datasets.