Comments (5)
The existing label assignments can be found in: https://github.com/CyberReboot/PoseidonML/blob/master/DeviceClassifier/OneLayer/opts/label_assignments.json
from networkml.
Ah, thanks @cglewis, I had a configuration problem and it wasn't reading in the file appropriately. Your output of a successful run helped me narrow it down :)
from networkml.
Hi, do you have some documentation where i can find the correct number?
from networkml.
Hi, I was attempting to get a handle on PoseidonML so I could fix this issue and had a problem with the data set I obtained from https://iotanalytics.unsw.edu.au , specifically 16-09-28.pcap and 16-10-04.pcap. I get the following message: INFO:__main__:Not enough sessions in pcap
Is there an already available data set that I can use? Or is there some special post-processing I need to do on the above PCAP files?
from networkml.
@DanSibbernsen the not enough sessions in pcap message happens when there's less than 5 sessions in the capture for the primary IP that is being evaluated. I ran the OneLayer eval on both 16-09-29.pcap
and 16-09-23.pcap
from here: https://iotanalytics.unsw.edu.au/iottraces.html
Here are the results I got respectively:
$ export PCAP=~/Downloads/16-09-29.pcap
$ make
Sending build context to Docker daemon 7.536MB
...
Running OneLayer Eval on PCAP file ~/Downloads/16-09-29.pcap
INFO:__main__:Unknown : 0.955
INFO:__main__:GPU laptop : 0.024
INFO:__main__:Business workstation : 0.008
INFO:__main__:Message: {"ec:1a:59:83:28:11": {"timestamp": 1475071484.695704, "decisions": {"behavior": "normal", "investigate": true}, "classification": {"labels": ["Unknown", "GPU laptop", "Business workstation"], "confidences": [0.9553587485600846, 0.024370670652594937, 0.008152348557037191]}, "valid": false}}
$ export PCAP=~/Downloads/16-09-23.pcap
$ make
Sending build context to Docker daemon 7.536MB
...
Running OneLayer Eval on PCAP file ~/Downloads/16-09-23.pcap
INFO:__main__:Unknown : 0.955
INFO:__main__:GPU laptop : 0.025
INFO:__main__:Business workstation : 0.008
INFO:__main__:Message: {"ec:1a:59:83:28:11": {"timestamp": 1474553101.338756, "classification": {"labels": ["Unknown", "GPU laptop", "Business workstation"], "confidences": [0.9553420454242527, 0.024672997138479827, 0.00792211967226373]}, "valid": false, "decisions": {"investigate": true, "behavior": "normal"}}}
from networkml.
Related Issues (20)
- make Redis optional
- warnings and deprecations need to be cleaned up HOT 2
- re-format rabbit message
- some pcaps will throw a traceback HOT 4
- `make help` throws an EOF
- Tensorflow2 Code Not Idiomatic HOT 1
- Zero features found from small PCAPs error HOT 1
- bad len packets throw traceback in reader.py HOT 3
- networkml uses TCP/IP or UDP/IP only HOT 1
- Import deprecation warnings
- Version mismatch for pickled files
- IPv6 is broken due to the index of fields being hardcoded HOT 2
- Runtime warnings HOT 1
- source_mac cuts off the first value
- Issue in standalone dev environment HOT 7
- Is threshold_time missing from Model creation? HOT 2
- Add flag to choose canonical source MAC
- Action Required: Fix Renovate Configuration HOT 1
- pandas 1.3.0 sometimes fails to calculate quantile 0.75
- Dependency Dashboard
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from networkml.