Projects > Pathological Lung Segmentation  

Malicious Network Traffic Detection


Publications and Further Reading

Learning detectors of malicious web requests for intrusion detection in network traffic
Lukas Machlica, Karel Bartos, and Michal Sofka arXiv:1702.02530 [stat.ML] 2017.
[pdf] [bibtex] [arXiv]

Instances hits Instances distributions

Learning Invariant Representation for Malicious Network Traffic Detection
Vojtech Franc, Michal Sofka, and Karel Bartos
In Proceedings of the European Conference on Artificial Intelligence, Hague, Holland, 29 Aug - 2 Sep. 2016.
[pdf] [bibtex] [slides]

Equidistant bins Learned bins

Optimized Invariant Representation of Network Traffic for Detecting Unseen Malware Variants
Vojtech Franc, Michal Sofka, and Karel Bartos
USENIX Security Symposium, Austin, TX, 10-12 Aug. 2016. 15.6% acceptatnce rate.
[pdf] [bibtex]

Hits vs. Detections MIL in 2D

Learning detector of malicious network traffic from weak labels
Vojtech Franc, Michal Sofka, and Karel Bartos
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Porto, Portugal, 7-11 Sep. 2015.
[pdf] [bibtex] [website] [publisher]

Clusters Self-similarity

Robust representation of network traffic for detecting malware variations
Karel Bartos and Michal Sofka
In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Porto, Portugal, 7-11 Sep. 2015.
[pdf] [bibtex] [website] [publisher]



 

Copyright 2017 Michal Sofka