This repository contains the code of our take on solving the problem of Shilling attacks.
We achieved the following tasks in our project:
- Designed multiple recommendation models based on User-User CF,Item-Item CF and Content based filtering.
- Performed various shilling attacks on each of the model to manipulate their behaviour and analyse the bias introduced.
- Modelled a detection algorithm to identify and remove the shilling attacker profiles.
I presented our research at the 9th ICCCNT conference held in IISc Bengaluru. Link to our research paper.