Our team is excited to share the latest news and features of Slips, our behavioral-based machine learning intrusion detection system.
Quick links:
Download Slips from our GitHub repository: https://github.com/stratosphereips/StratosphereLinuxIPS
Access Slips documentation through Read the Docs: https://stratospherelinuxips.readthedocs.io/en/develop/
What We Are Particularly Excited About
In this release we are particularly excited about these new Slips features:
- Expand Immune dataset documentation with performance evaluations and bottleneck analysis.
- Improve horizontal, vertical, and ICMP portscan detection logic and speed.
- Improve handling of high-throughput traffic.
- Optimize profiler architecture: backpressure, dynamic worker scaling, true multiprocessing.
- Reduce false positives for "public IPs outside of localnet" evidence.
- Reduce the number of duplicate port scan evidence by using a log scale.
- Speed up Github CI testing.
- Speed up Slips processing and reduce RAM usage.
- Suppress duplicate “unknown port” evidence for every scanned port when a portscan is detected.
- Fix the evidence button in the web interface.
Check the full list of changes in our release page: https://github.com/stratosphereips/StratosphereLinuxIPS/releases/tag/v1.1.17
Learn more!
Wondering what Slips is capable of? Check out these demo presentations:
LCN conference in 2021: https://youtu.be/1KqwlxVuf48
BlackHat USA Arsenal 2022: https://youtu.be/dJuTmi2bJcI
How to contribute
For those interested in contributing to Slips:
https://stratospherelinuxips.readthedocs.io/en/develop/contributing.html
https://www.stratosphereips.org/blog/2022/6/6/writing-a-slips-module
https://stratospherelinuxips.readthedocs.io/en/develop/slips_in_action.html
Get in Touch
Feel free to join our Discord server and ask questions, suggest new features or give us feedback. PRs and Issues are welcomed in our repo.