Day 14 in the Advent of Cyber 2023. The CTO has made our toy pipeline go wrong. By infecting elves at key positions in the toy-making process, he has poisoned the pipeline and caused the elves to make defective toys! McSkidy has started to combat the problem by placing control elves in the pipeline. These elves take measurements of the toys to try and narrow down the exact location of problematic elves in the pipeline by comparing the measurements of defective and perfect toys. However, this is an incredibly tedious and lengthy process, so he's looking to use machine learning to optimise it.
WARNING: Spoilers and challenge-answers are provided in the following writeup.
Official walk-through video is as well available at Youtube - UnixGuy | Cyber Security.
Day 14 - The Little Machine That Wanted to Learn
Artificial Intelligence or Machine Learning has had a profound impact across industries over the last couple of years. It's much more than complex IF-statements, CASE-switches and what not, as it is trained on data and used to predict an output or verdict that we then can use in our analytical work, for predicting failure-rates and alike. It can be used to raise the efficiency and to some degree our accuracy.
The Challenge
In the challenge we're given an introduction to Machine Learning, and the first few questions revolve around reading this introduction.
For the last question, we need to build a neural network in python to train on provided data, upload the output predictions file predictions.txt to the provided page websiteforpredictions.thm:8000 on the attached machine, and then we are granted the flag if the accuracy is above 90%.
Implementing the last few code-lines as described in the challenge-description in the provided file detector.py and running it, we do get quite a good network accuracy from the start and do not have to run another learning/training session.
