Attacking Black-box Recommendations via Copying Cross-domain User Profiles

TL;DR

This paper introduces CopyAttack, a reinforcement learning-based black-box attack that copies real user profiles across domains to manipulate recommendations, exposing vulnerabilities in deep learning recommender systems.

Contribution

The paper presents a novel RL-based framework for creating realistic profile injection attacks by copying cross-domain user profiles, enhancing attack effectiveness against deep learning recommenders.

Findings

CopyAttack significantly increases hit ratios of targeted items.

The framework effectively learns to select and refine user profiles.

Experiments confirm the attack's success on real-world datasets.

Abstract

Recently, recommender systems that aim to suggest personalized lists of items for users to interact with online have drawn a lot of attention. In fact, many of these state-of-the-art techniques have been deep learning based. Recent studies have shown that these deep learning models (in particular for recommendation systems) are vulnerable to attacks, such as data poisoning, which generates users to promote a selected set of items. However, more recently, defense strategies have been developed to detect these generated users with fake profiles. Thus, advanced injection attacks of creating more `realistic' user profiles to promote a set of items is still a key challenge in the domain of deep learning based recommender systems. In this work, we present our framework CopyAttack, which is a reinforcement learning based black-box attack method that harnesses real users from a source domain by copying their profiles into the target domain with the goal of promoting a subset of items. CopyAttack is constructed to both efficiently and effectively learn policy gradient networks that first select, and then further refine/craft, user profiles from the source domain to ultimately copy into the target domain. CopyAttack's goal is to maximize the hit ratio of the targeted items in the Top-$k$ recommendation list of the users in the target domain. We have conducted experiments on two real-world datasets and have empirically verified the effectiveness of our proposed framework and furthermore performed a thorough model analysis.