Influence Function based Data Poisoning Attacks to Top-N Recommender Systems

Abstract

Recommender system is an essential component of web services to engage users. Popular recommender systems model user preferences and item properties using a large amount of crowdsourced user-item interaction data, e.g., rating scores; then top-$N$ items that match the best with a user's preference are recommended to the user. In this work, we show that an attacker can launch a data poisoning attack to a recommender system to make recommendations as the attacker desires via injecting fake users with carefully crafted user-item interaction data. Specifically, an attacker can trick a recommender system to recommend a target item to as many normal users as possible. We focus on matrix factorization based recommender systems because they have been widely deployed in industry. Given the number of fake users the attacker can inject, we formulate the crafting of rating scores for the fake users as an optimization problem. However, this optimization problem is challenging to solve as it is a non-convex integer programming problem. To address the challenge, we develop several techniques to approximately solve the optimization problem. For instance, we leverage influence function to select a subset of normal users who are influential to the recommendations and solve our formulated optimization problem based on these influential users. Our results show that our attacks are effective and outperform existing methods.

arXiv commentAccepted by WWW 2020; This is technical report version

References in corpus (14)

• Understanding Black-box Predictions via Influence Functions
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Adversarial Attacks on Neural Networks for Graph Data
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Poisoning Attacks against Support Vector Machines
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• Is feature selection secure against training data poisoning?
• Poisoning Attacks to Graph-Based Recommender Systems
• Data Poisoning Attacks on Factorization-Based Collaborative Filtering
• On the Accuracy of Influence Functions for Measuring Group Effects
• Data Dropout: Optimizing Training Data for Convolutional Neural Networks
• Attacking Graph-based Classification via Manipulating the Graph Structure
• Byzantine-Resilient Stochastic Gradient Descent for Distributed Learning: A Lipschitz-Inspired Coordinate-wise Median Approach
• Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach