Changes:
* Add support for scikit-learn MLPClassifier ([276](https://github.com/AI-SDC/SACRO-ML/pull/276))
* Use default XGBoost params if not defined in structural attacks ([277](https://github.com/AI-SDC/SACRO-ML/pull/277))
* Clean up documentation ([282](https://github.com/AI-SDC/SACRO-ML/pull/282))
* Clean up repository and update packaging ([283](https://github.com/AI-SDC/SACRO-ML/pull/283))
* Format docstrings ([286](https://github.com/AI-SDC/SACRO-ML/pull/286))
* Refactor ([284](https://github.com/AI-SDC/SACRO-ML/pull/284), [#285](https://github.com/AI-SDC/SACRO-ML/pull/285), [#287](https://github.com/AI-SDC/SACRO-ML/pull/287))
* Add CLI and tools for generating configs; significant refactor ([291](https://github.com/AI-SDC/SACRO-ML/pull/291))
* Add different implementation modes for online and offline LiRA ([281](https://github.com/AI-SDC/SACRO-ML/pull/281))