Skip to content

Latest commit

 

History

History
11 lines (7 loc) · 771 Bytes

README.md

File metadata and controls

11 lines (7 loc) · 771 Bytes
Raw

Advancing recommender systems by mitigating shilling attacks

This repository contains the code of our take on solving the problem of Shilling attacks.

We achieved the following tasks in our project:

  1. Designed multiple recommendation models based on User-User CF,Item-Item CF and Content based filtering.
  2. Performed various shilling attacks on each of the model to manipulate their behaviour and analyse the bias introduced.
  3. 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.