Summary of Semi-supervised Learning For Anomaly Traffic Detection Via Bidirectional Normalizing Flows, by Zhangxuan Dang et al.
Semi-Supervised Learning for Anomaly Traffic Detection via Bidirectional Normalizing Flows
by Zhangxuan Dang, Yu Zheng, Xinglin Lin, Chunlei Peng, Qiuyu Chen, Xinbo Gao
First submitted to arxiv on: 13 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a three-stage anomaly detection framework for network traffic, leveraging only normal traffic to generate pseudo anomaly samples. The framework consists of reconstruction, normalization, and generation modules. First, a deep representation is learned from normal samples using a reconstruction method. Then, these representations are normalized using a bidirectional flow module. To simulate anomalies, noises are added to the normalized representations, which are then passed through the generation direction of the bidirectional flow module. A simple classifier is trained to differentiate between normal and pseudo anomaly samples in the latent space. The framework achieves state-of-the-art results on common benchmarking datasets for anomaly network traffic detection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps keep internet networks safe by detecting unusual traffic patterns. To do this, it creates fake versions of these abnormal patterns using only normal data. This approach is more efficient than previous methods because it requires less computer power and storage space. The research team tested their method on several datasets and found that it performed better than existing approaches. |
Keywords
* Artificial intelligence * Anomaly detection * Latent space
