Advancing Recommender Systems by mitigating Shilling attacks

TL;DR

This paper presents an algorithm to detect shilling profiles in recommender systems, addressing the vulnerability of collaborative filtering to malicious attacks that bias recommendations.

Contribution

It introduces a novel detection algorithm for shilling profiles and analyzes their impact on recommendation quality.

Findings

The proposed algorithm accurately identifies shilling profiles.

Shilling attacks significantly distort recommendation outputs.

Detection improves system robustness against malicious manipulations.

Abstract

Considering the premise that the number of products offered grow in an exponential fashion and the amount of data that a user can assimilate before making a decision is relatively small, recommender systems help in categorizing content according to user preferences. Collaborative filtering is a widely used method for computing recommendations due to its good performance. But, this method makes the system vulnerable to attacks which try to bias the recommendations. These attacks, known as 'shilling attacks' are performed to push an item or nuke an item in the system. This paper proposes an algorithm to detect such shilling profiles in the system accurately and also study the effects of such profiles on the recommendations.