Deep Learning for Adaptive Intrusion Detection in Open-World: A Survey

In open-world environments, network intrusion detection faces challenges such as unknown attacks, distribution shifts, and data scarcity, where traditional methods often struggle with generalization and adaptability. This paper surveys recent advances in deep learning-based approaches to address these challenges, and reviews major research directions from the perspectives of model capabilities and open-environment demands. By analyzing the strengths and limitations of different techniques, we provide a comprehensive reference for selecting appropriate methods under varying open-world conditions. Furthermore, we highlight the need for future research to balance model flexibility, robustness, and trustworthiness to advance intrusion detection systems toward more intelligent and practical solutions.