Attacked connection detection using AE, VAE and GMM

AUTHORS： Yixuan Ren, Zhuoer Shen, Jiahui Zhang

The demos are shown at the main branch with result in ipynb file.

The detailed coding and files are at the other branch.

DEMO

Demo 1 : Dataset distribution visualization

Demo 2: CICIDS 2017 using AE with 40k samples

Demo 3: CICIDS 2017 using AE with full samples

Demo 4: CICIDS 2017 using GMM and VAE

Demo 5: KDD CUP 99 using AE, VAE, GMM

DATASETS

To run the demo, please download the dataset from the official website.

Due to github limitation, sorry we cannot upload the big dataset.

KDD CUP 99: https://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html

CICIDS 2017: https://www.kaggle.com/datasets/cicdataset/cicids2017

References

1. Jinwon An and Sungzoon Cho, "Variational autoencoder based anomaly detection using reconstruction probability," Special Lecture on IE, 21(1):1–18, 2015.
2. Zhaomin Chen, Chai Kiat Yeo, Bu Sung Lee, and Chiew Tong Lau, "Autoencoder-based network anomaly detection," in 2018 Wireless telecommunications symposium (WTS), pp. 1-5. IEEE, 2018.
3. David E. Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams, "Learning internal representations by error propagation," 1986. Available at Semantic Scholar.
4. Chong Zhou and Randy C Paffenroth, "Anomaly detection with robust deep autoencoders," in Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 665–674, 2017.
5. Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, and Haifeng Chen, "Deep autoencoding gaussian mixture model for unsupervised anomaly detection," in International conference on learning representations, 2018.
6. https://github.com/CharlieDDDD/KDD-Cup-99-CNN-PyTorch?tab=readme-ov-file
7. https://docs.seldon.io/projects/alibi-detect/en/latest/examples/od_vae_kddcup.html
8. https://github.com/danieltan07/dagmm/?tab=readme-ov-file
9. https://github.com/brett-gt/IntrusionDetectionSystem
10. https://github.com/mperezcarrasco/PyTorch-DAGMM

Thanks.