perfspec-learning/about.md

Table of Contents

• PerfSPEC Learning Phase - ABOUT
• What is done so far ?
• Plans
• Tools and enviroment
• PerfSPEC
• In Review
• Reference

PerfSPEC Learning Phase - ABOUT

Based in PerfSPEC: Performance Profiling-based Proactive Security Policy Enforcement for Containers document presented in [1], this repository contains source files used to generate and process data.

For more PerfSPEC info use:

• Main description
• Introduction
• Reference document
• Presentación in Spanish
• How to install
• Autogenerated graph view of actions and events distribution

What is done so far ?

• Good look and feel and interactions among processing, analisys and presentation layers
• Use better software packages management like uv to complement Python pip
• Use an open and compatible notebook like Marimo to support alternative dataframes engines like Polars rather than Pandas
• Use settings and structures to play with different settinigs and options
• Implement one customized LSTM model within notebooks
• Use of different metrics to apply to the training models with custumezable adjustments and checkpoints
• Use notebooks as python scripts for command-line use cases like collect predictions or automatic train models
• Use Dry to reuse code and centralize common tasks like settings or loading resources. This is main use and existence of lib_perfspec.py
• Splitting basic tasks among several specific notebooks:
  • Preprocessing data collection to generate clean and usefull (critical actions) info to train models and ranking prepare_perfspec.py
  • Train models to get predictions train_perfspec.py
  • Get predictions from existing models run_perfspec.py
  • Review and analisys trained models for better results model_perfspec.py

Plans

Tools and enviroment

• Use Polars by default
• Use [Nushell](https://www.nushell.sh/] for command-line interfrace and data processing
• Try Rust Machine Learning as alternative or complement of Keras / TensorFlow requiremens
• Incorporate other training models and [Large language model][LLM]

PerfSPEC

• Borrow some parts to PerfSPEC Ranking Phase in classify and measure resources and performance costs
• Analisys and connection with other parts of PerfSPEC design and reference like Ranking and Runtime phases

In Review

• Check predictions accuracy
• Validate data procedures and results
• Verify and test use cases

Reference

[1]: H. Kermabon-Bobinnec et al., "PerfSPEC: Performance Profiling-based Proactive Security Policy Enforcement for Containers," in IEEE Transactions on Dependable and Secure Computing, doi: 10.1109/TDSC.2024.3420712.