Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912653117489152 |
|---|---|
| author | Roy, Padmaksha Cody, Tyler Singhal, Himanshu Choi, Kevin Jin, Ming |
| author_facet | Roy, Padmaksha Cody, Tyler Singhal, Himanshu Choi, Kevin Jin, Ming |
| contents | Zero-day anomaly detection is critical in industrial applications where novel, unforeseen threats can compromise system integrity and safety. Traditional detection systems often fail to identify these unseen anomalies due to their reliance on in-distribution data. Domain generalization addresses this gap by leveraging knowledge from multiple known domains to detect out-of-distribution events. In this work, we introduce a multi-task representation learning technique that fuses information across related domains into a unified latent space. By jointly optimizing classification, reconstruction, and mutual information regularization losses, our method learns a minimal(bottleneck), domain-invariant representation that discards spurious correlations. This latent space decorrelation enhances generalization, enabling the detection of anomalies in unseen domains. Our experimental results demonstrate significant improvements in zero-day or novel anomaly detection across diverse anomaly detection datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_17300 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space Roy, Padmaksha Cody, Tyler Singhal, Himanshu Choi, Kevin Jin, Ming Cryptography and Security Machine Learning Zero-day anomaly detection is critical in industrial applications where novel, unforeseen threats can compromise system integrity and safety. Traditional detection systems often fail to identify these unseen anomalies due to their reliance on in-distribution data. Domain generalization addresses this gap by leveraging knowledge from multiple known domains to detect out-of-distribution events. In this work, we introduce a multi-task representation learning technique that fuses information across related domains into a unified latent space. By jointly optimizing classification, reconstruction, and mutual information regularization losses, our method learns a minimal(bottleneck), domain-invariant representation that discards spurious correlations. This latent space decorrelation enhances generalization, enabling the detection of anomalies in unseen domains. Our experimental results demonstrate significant improvements in zero-day or novel anomaly detection across diverse anomaly detection datasets. |
| title | Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2312.17300 |