- Update dependency pyshark to v0.4.5
- Update dependency cython to v0.29.28
- Update dependency humanize to v4.0.0
- Update dependency pytest to v7.1.1
- Update dependency pbr to v5.8.1
- Update dependency numpy to v1.22.3
- Update dependency pandas to v1.4.1
- Update dependency pytest-rabbitmq to v2.2.1
- Update iqtlabs/rbqwrapper Docker tag to v0.11.32
- Update dependency pbr to v5.8.0
- Update iqtlabs/rbqwrapper Docker tag to v0.11.31
- Update dependency humanize to v3.13.1
- Update dependency nest_asyncio to v1.5.4
- Update dependency cython to v0.29.26
- Update dependency pytest-xdist to v2.5.0
- Update dependency pygments to v2.11.2
- Update dependency numpy to v1.22.0
- Update dependency pandas to v1.3.5
- Update dependency scikit-learn to v1.0.2
- Update dependency numpy to v1.21.3
- Update dependency pandas to v1.3.4
- Update dependency scikit-learn to v1.0.1
- Update dependency joblib to v1.1.0
- Update dependency humanize to v3.12.0
- Update dependency pytest-cov to v3
- Update dependency pytest-xdist to v2.4.0
- Update codecov/codecov-action action to v2.1.0
- Allow pcap to features to read a pcap CSV with pre-cast int types (for future drop in replacement for tshark/pyshark parsers). If hex int fields, are detected as strings, fall back to current behavior (use python conversion)
- Update iqtlabs/rbqwrapper Docker tag to v0.11.29
- pytype observes that csv.DictWriter fields, should be an indexable Sequence
- Updated humanize, numpy, pandas, and pygments
- Updated rbqwrapper base image
- Fixed an issue where tshark could exit and not write out buffer
- Improved SAAST scanning
- Updated NumPy, codecov-action, reorder_python_imports, upload-artifact
- Pinned Pandas to v1.2.5 due to #871
- Added Shift-Left SAAST Scan on push and PR
- Updated humanize, pytest-xdist, NumPy, Pandas, python, pip, cython
- Updated humanize, pytest-cov, pytest-rabbitmq, codecov-action
- Updated pre-commit, rbqwrapper, and pytest-cov
- Fixed output for Packet Cafe consumption
- Updated codecov, reorder_python_imports, cython, humanize, numpy, pandas, pbr, scikit-learn, pygments, and pytest
- Updated rbqwrapper, cython, pandas, and pygments
- Updated reorder_python_imports, rbqwrapper, joblib, numpy, pandas, pyshark, and pytest-xdist
- Updated pytest, pytest-cov, scikit-learn, pandas, nest_asyncio
- Updated codecov, pygments, pytest, pytest-xdist, pytest-rabbitmq
- Moved base image to rbqwrapper, abstracting away RabbitMQ
- Added a new feature for listing out features in the model
- Rewrote the model serializer removing the need for sklearn_json
- Add end-to-end tests
- Move to PBR
- fix test for 'behavior'
- Rollback numpy as it doesn't properly handle confidence values on ARM64
- Updated pre-commit versions
- Cleaned up formatting/style
- Updated numpy, pandas, and nest_asyncio
- Updated numpy, pygments, pytest, and nest_asyncio
- Updated buildx, codecov, humanize, joblib, pandas, pygments, pytest, and nest_asyncio
- Updated humanize, pytest-cov, pytest-xdist, and pandas
- Retrained models for updated version of scikit-learn
- Udpated scikit-learn and pytest
- Moved from CyberReboot to new IQTLabs brand
- Updated cython, humanize, netaddr, numpy, pandas, pytest, pytest-xdist, and nest_asyncio
- Updated joblib, pandas, numpy, netaddr, and humanize
- Moved Docker base image to python:3.8-slim (debian based instead of alpine)
- Updated pandas, pytest-cov
- Broke up Docker into two images for build times across architectures
- Updated joblib, pandas, pytest, pytest-cov, and pyshark
- Updated documentation for developers
- Updated pytest-xdist, nest-asyncio, and numpy
- Added flag --no-srcmacid to make predictions on all MACs found
- Actually fix manifest to properly include models for PyPi Package.
- Added missing files to manifest for PyPi package.
- Rolling back to latest published version of pyshark - for issues see commented version in requirements.txt, which is unfortunately not supported for dependency install from PyPi with pip.
- Rewrote Networkml entirely
- Now only does classification, no longer behavior
- Flexible stages for processing PCAPs into CSVs of features
- No longer uses tensorflow
- Now supports running on ARM
- Fixed local dev python version to be 3.7
- Fixed missing threshold_time configuration option
- Fixed filename checks for client/server
- Warn instead of debug log when files are ignored
- Fixed running concurrent.futures when on python3.6
- Added caching for parsed sessions
- Added IPv6 capability to networkML
- Updated pytest to v5.3.4
- Updated models for scikit v0.22.1
- Updated redis to v3.4.1
- Updated tensorflow
- Updated pyshark
- Made sessionizer parallel
- Added 120 minute timeout for a pcap
- Added sessionizer test
- Updated license
- Updated numpy to 1.18.0
- updated pytest-xdist to 1.31.0
- Updated test_extract_macs() test
- Removed vent template
- Added check for empty F1 score list
- Add pyshark wiring to get highest-level protocol
- Make tests run in parallel
- Update models for scikit-learn v0.22
- Improve parsing speed
- Add tests for pcap reader
- update pytest to 5.3.1
- update scikit-learn to 0.22
- Updated numpy to 1.17.4
- Updated pytest to 5.3
- Edited .gitignore
- Added tests for label extraction
- Added test for avx check
- Added pcap labels to decision
- updated numpy to 1.17.3
- updated pytest to 5.2.2
- Added documentation
- Added support for additional labels and filenames
- Updated pytest-cov
- Updated pytest
- Updated redis
- Added more documentation and tests
- Updated the python image for the Dockerfile
- Updated pytest to 5.2.0
- Updated tensorflow to 2.0.0
- Fixed up old code using tensorflow1 to work with tensorflow2
- Updated pytest to 5.1.2
- Updated numpy to 1.17.2
- Fixed make help
- Updated redis to 3.3.8
- Updated pytest to 5.1.1
- Updated redis to 3.3.7
- Redis is now optional
- RabbitMQ is now configurable, and has a cleaned up message format
- Retrained models against numpy 1.17.0 and scikit-learn 0.21.3
- Updated pika to 1.1.0
- Got rid of outdated linux headers
- Updated redis to 3.3.4
- Updated to python3.7
- Updated models
- Updated tensorflow to 1.14.0
- Updated pytest to 5.0.1
- Updated models and included printers
- Renamed PoseidonML to NetworkML
- Updated pytest to 4.6.3
- Updated numpy to 1.16.3
- Updated pytest-cov to 2.7.1
- Updated pytest to 4.5.0
- Reduce places that Tensorflow is imported
- Made it possible to run classifications on CPUs that don't support AVX
- Updated Tensorflow imports for new deprecations
- Updated pika to 1.0.1
- Removed a bunch of duplicated code to keep the code base cleaner
- Added a bunch of tests to get coverage up to 90%
- Updated pytest to 4.4.1
- Removed the use of md5 and replaced it with sha224
- Major rewrite and restructuring of the code base, but same functionality
- Changed the default for Rabbit to not be used
- Changed the environment variable for Rabbit from SKIP_RABBIT to RABBIT
- Improved logging output for summarizing evaluation results of multiple PCAPs
- Updated versions of pika, pytest, redis, and scikit-learn
- Fixed a bug that was preventing training the SoSModel
- Added some more test coverage
- Updated the trained models and labels
- Updated tensorflow from 1.12.0 to 1.13.1.
- Updated numpy from 1.16.1 to 1.16.2.
- Miscellaneous error checking and spacing corrections.
- Updated pytest to 4.3.0 from 4.2.0.
- Cleaned up some code issues as pointed out by Codacy.
- Minor miscellaneous bugfixes to support running training natively.
- Provided a way to run DeviceClassifier training and testing scripts from command line.
- Cleaned up some unused code and consolidated common operations into utils and model class.
- Fixed issue where Makefile built the OneLayer training container when building the test one.
- Updated redis to 3.1.0
- Updated numpy to 1.16.1
- Updated numpy to 1.16.0
- Updated pika to 0.13.0
- Included a conda yml file for a standalone/dev environment, and new Makefile options to build it.
- models have been retrained to fix a warning about invalid results when evaluating a pcap
- some unused code and module has been removed
- upgraded pytest to 4.1.0 and pytest-cov to 2.6.1
- upgraded scikit-learn to 0.20.2
- removed scipy
- cleaned up requirements.txt and setup.py
- fixed issue where redis was throwing error when saving decisions
- fixed error in eval_onelayer that was using nonexistent key
- Make train/eval/test process consistent for all models
- Fixed path error specific to python 3.5 that occurred when processing PCAP files
- PCAP directories can now be used when running model evals
- upgraded pytest to 4.0.2
- upgraded scikit-learn to 0.20.1
- improved README documentation
- upgraded redis to 3.0.1
- added pcap directory support
- re-enabled the behavior model
- includes the trained behavior model
- fixed hardcoded onelayer pickle file in randomforest
- fixed missing labels
- simplified rabbit connection
- replaced deprecated randomized logistic regression with random forest
- upgraded pytest to 3.9.1
- fixed a NoneType error when multiplying
- fixed an issue where the config file wasn't being read properly
- abstracted away the code to read the config file into one place
- lots of cleanup of duplicated code
- upgraded tensorflow to 1.11.0
- upgraded scikit-learn to 0.20.0
- updated the model
- moved a bunch of duplicated code into common utils
- fixed issue where results were not getting sent to rabbitmq or stored in redis
- cleaned up cruft in OneLayer Eval
- moved OneLayer Eval code into a class to reduce duplication
- upgraded pytest to 3.8.0
- upgraded pytest-cov to 2.6.0
- upgraded tensorflow to 1.10.1
- made all print statements logger statements
- sends messages to rabbitmq now even if not enough sessions
- stores normal/abnormal results in redis now
- fixed performance issue where evaluation would take a long time
- updated the model
- upgraded pytest to 3.7.2
- upgraded numpy to 1.15.1
- updated model
- upgraded pytest to 3.7.1
- upgraded scikit-learn to 0.19.2
- linting
- fixes pairs issue when checking private addresses
- fixes the models path for running in a container
- improve dockerfile builds
- upgraded pika to 0.12.0
- upgraded scipy to 1.1.0
- upgraded numpy to 1.14.5
- upgraded tensorflow to 1.9.0
- fixed vent template
- added some initial tests
- re-trained the onelayer model with improved accuracy
- reduced the number of labels for onelayer to 6
- improvements for developing on poseidonml
- initial utility release