The Role of Fake Users in Sequential Recommender Systems

TL;DR

This paper empirically examines how fake users engaging in various behaviors impact the robustness of sequential recommender systems, revealing significant vulnerabilities especially in RLS metrics.

Contribution

It provides the first comprehensive empirical analysis of fake user impacts on SRS performance, highlighting the need for more resilient models against adversarial behaviors.

Findings

NDCG remains stable despite fake users

RLS metrics are severely degraded by fake users

Fake users can reduce RLS to near-zero values

Abstract

Sequential Recommender Systems (SRSs) are widely used to model user behavior over time, yet their robustness remains an under-explored area of research. In this paper, we conduct an empirical study to assess how the presence of fake users, who engage in random interactions, follow popular or unpopular items, or focus on a single genre, impacts the performance of SRSs in real-world scenarios. We evaluate two SRS models across multiple datasets, using established metrics such as Normalized Discounted Cumulative Gain (NDCG) and Rank Sensitivity List (RLS) to measure performance. While traditional metrics like NDCG remain relatively stable, our findings reveal that the presence of fake users severely degrades RLS metrics, often reducing them to near-zero values. These results highlight the need for further investigation into the effects of fake users on training data and emphasize the importance of developing more resilient SRSs that can withstand different types of adversarial attacks.