Attack Detection Using Item Vector Shift in Matrix Factorisation Recommenders

TL;DR

This paper introduces an unsupervised method for detecting shilling attacks in matrix factorization recommender systems by analyzing shifts in item preference vectors, offering a new approach that outperforms existing techniques.

Contribution

It presents a novel unsupervised detection technique based on item vector shifts, differing from prior supervised or distribution-based methods.

Findings

Effective in various attack scenarios

Detects obfuscated attack profiles

Outperforms existing detection methods

Abstract

This paper proposes a novel method for detecting shilling attacks in Matrix Factorization (MF)-based Recommender Systems (RS), in which attackers use false user-item feedback to promote a specific item. Unlike existing methods that use either use supervised learning to distinguish between attack and genuine profiles or analyse target item rating distributions to detect false ratings, our method uses an unsupervised technique to detect false ratings by examining shifts in item preference vectors that exploit rating deviations and user characteristics, making it a promising new direction. The experimental results demonstrate the effectiveness of our approach in various attack scenarios, including those involving obfuscation techniques.