Data Poisoning Attacks on Factorization-Based Collaborative Filtering

Abstract

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in the industry, their outputs could affect business decision making, introducing incentives for an adversarial party to compromise the availability or integrity of such systems. We introduce a data poisoning attack on collaborative filtering systems. We demonstrate how a powerful attacker with full knowledge of the learner can generate malicious data so as to maximize his/her malicious objectives, while at the same time mimicking normal user behavior to avoid being detected. While the complete knowledge assumption seems extreme, it enables a robust assessment of the vulnerability of collaborative filtering schemes to highly motivated attacks. We present efficient solutions for two popular factorization-based collaborative filtering algorithms: the \emph{alternative minimization} formulation and the \emph{nuclear norm minimization} method. Finally, we test the effectiveness of our proposed algorithms on real-world data and discuss potential defensive strategies.

Cited by in corpus (38)

• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Adversarial Attacks on Neural Networks for Graph Data
• Adversarial Attacks and Defences: A Survey
• Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
• Poisoning Attacks to Graph-Based Recommender Systems
• Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
• Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
• Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
• Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
• Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems
• Attacking Recommender Systems with Augmented User Profiles
• Shilling Black-box Recommender Systems by Learning to Generate Fake User Profiles
• Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
• Stealing Hyperparameters in Machine Learning
• Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios
• Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
• Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
• FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping
• A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks
• Dataset Distillation
• Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defense
• Adversarial Attacks on Linear Contextual Bandits
• Attacking Graph-based Classification via Manipulating the Graph Structure
• Poisoning Attacks to Local Differential Privacy Protocols for Key-Value Data
• Preventing the Popular Item Embedding Based Attack in Federated Recommendations
• Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges
• Model-Targeted Poisoning Attacks with Provable Convergence
• Influence Function based Data Poisoning Attacks to Top-N Recommender Systems
• Data Poisoning Attacks to Local Differential Privacy Protocols
• Attacking Black-box Recommendations via Copying Cross-domain User Profiles
• Data Poisoning Attacks on Neighborhood-based Recommender Systems
• Adversarial Item Promotion: Vulnerabilities at the Core of Top-N Recommenders that Use Images to Address Cold Start
• Uplift Modeling for Target User Attacks on Recommender Systems
• Reinforcement Learning for Autonomous Defence in Software-Defined Networking
• 10 Security and Privacy Problems in Large Foundation Models
• Incentives in Two-sided Matching Markets with Prediction-enhanced Preference-formation
• Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework
• Poisoning Online Learning Filters: DDoS Attacks and Countermeasures