Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space

arXiv:2312.17300v3 Announce Type: replace-cross
Abstract: Domain generalization focuses on leveraging knowledge from multiple related domains with ample training data and labels to enhance inference on unseen in-distribution (IN) and out-of-distribution (OOD) domains. In our study, we introduce a two-phase representation learning technique using multi-task learning. This approach aims to cultivate a latent space from features spanning multiple domains, encompassing both native and cross-domains, to amplify generalization to IN and OOD territories. Additionally, we attempt to disentangle the latent space by …

abstract arxiv cs.cr cs.lg data detection distribution domain domains improving inference knowledge labels multiple multi-task learning representation representation learning space study training training data type