A Study on Transferability of Deep Learning Models for Network Intrusion Detection
This work addresses the problem of improving detection efficiency for cybersecurity practitioners, but it is incremental as it builds on existing methods without introducing new paradigms.
The study investigated the transferability of deep learning models across different attack classes in network intrusion detection, finding that data augmentation and preprocessing techniques can enhance model performance, with specific relationships being symmetric or asymmetric.
In this paper, we explore transferability in learning between different attack classes in a network intrusion detection setup. We evaluate transferability of attack classes by training a deep learning model with a specific attack class and testing it on a separate attack class. We observe the effects of real and synthetically generated data augmentation techniques on transferability. We investigate the nature of observed transferability relationships, which can be either symmetric or asymmetric. We also examine explainability of the transferability relationships using the recursive feature elimination algorithm. We study data preprocessing techniques to boost model performance. The code for this work can be found at https://github.com/ghosh64/transferability.