Who is Really Affected by Fraudulent Reviews? An analysis of shilling attacks on recommender systems in real-world scenarios

TL;DR

This paper investigates the impact of shilling attacks on recommender systems in real-world scenarios, analyzing how these attacks affect algorithm performance and identifying the user groups most vulnerable to manipulation.

Contribution

It provides the first real-world analysis quantifying the effects of shilling attacks on recommender systems and user susceptibility.

Findings

Shilling attacks significantly degrade recommender system accuracy.

Certain user groups are more vulnerable to fraudulent reviews.

The study highlights the need for robust defenses against shilling attacks.

Abstract

We present the results of an initial analysis conducted on a real-life setting to quantify the effect of shilling attacks on recommender systems. We focus on both algorithm performance as well as the types of users who are most affected by these attacks.