Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Comprehensive Survey on Trustworthy Recommender Systems

Wenqi Fan, Xiangyu Zhao, Xiao Chen, Jingran Su, Jingtong Gao, Lin Wang, Qidong Liu, Yiqi Wang, Han Xu, Lei Chen, Qing Li

TL;DR

The paper surveys Trustworthy Recommender Systems (TRec) across six core dimensions—Safety & Robustness, Non-discrimination & Fairness, Explainability, Privacy, Environmental Well-being, and Accountability & Auditability—outlining concepts, taxonomies, representative methods, applications, and available surveys/tools. It emphasizes the interdependencies among dimensions and highlights practical risks and defenses in real-world deployments. By detailing attack/defense paradigms, fairness frameworks, explainability strategies, privacy-preserving techniques, energy-efficient methods, and governance mechanisms, the work provides a comprehensive blueprint for building multi-dimensional trustworthy recommender systems. The analysis underlines future directions including cross-dimension interactions, ecosystem development, and standardized benchmarks to accelerate progress and trustworthy deployment in industry. Collectively, the paper establishes a multi-faceted framework for designing, evaluating, and auditing recommender systems with enhanced safety, fairness, transparency, privacy, sustainability, and accountability.

Abstract

As one of the most successful AI-powered applications, recommender systems aim to help people make appropriate decisions in an effective and efficient way, by providing personalized suggestions in many aspects of our lives, especially for various human-oriented online services such as e-commerce platforms and social media sites. In the past few decades, the rapid developments of recommender systems have significantly benefited human by creating economic value, saving time and effort, and promoting social good. However, recent studies have found that data-driven recommender systems can pose serious threats to users and society, such as spreading fake news to manipulate public opinion in social media sites, amplifying unfairness toward under-represented groups or individuals in job matching services, or inferring privacy information from recommendation results. Therefore, systems' trustworthiness has been attracting increasing attention from various aspects for mitigating negative impacts caused by recommender systems, so as to enhance the public's trust towards recommender systems techniques. In this survey, we provide a comprehensive overview of Trustworthy Recommender systems (TRec) with a specific focus on six of the most important aspects; namely, Safety & Robustness, Nondiscrimination & Fairness, Explainability, Privacy, Environmental Well-being, and Accountability & Auditability. For each aspect, we summarize the recent related technologies and discuss potential research directions to help achieve trustworthy recommender systems in the future.

A Comprehensive Survey on Trustworthy Recommender Systems

TL;DR

The paper surveys Trustworthy Recommender Systems (TRec) across six core dimensions—Safety & Robustness, Non-discrimination & Fairness, Explainability, Privacy, Environmental Well-being, and Accountability & Auditability—outlining concepts, taxonomies, representative methods, applications, and available surveys/tools. It emphasizes the interdependencies among dimensions and highlights practical risks and defenses in real-world deployments. By detailing attack/defense paradigms, fairness frameworks, explainability strategies, privacy-preserving techniques, energy-efficient methods, and governance mechanisms, the work provides a comprehensive blueprint for building multi-dimensional trustworthy recommender systems. The analysis underlines future directions including cross-dimension interactions, ecosystem development, and standardized benchmarks to accelerate progress and trustworthy deployment in industry. Collectively, the paper establishes a multi-faceted framework for designing, evaluating, and auditing recommender systems with enhanced safety, fairness, transparency, privacy, sustainability, and accountability.

Abstract

As one of the most successful AI-powered applications, recommender systems aim to help people make appropriate decisions in an effective and efficient way, by providing personalized suggestions in many aspects of our lives, especially for various human-oriented online services such as e-commerce platforms and social media sites. In the past few decades, the rapid developments of recommender systems have significantly benefited human by creating economic value, saving time and effort, and promoting social good. However, recent studies have found that data-driven recommender systems can pose serious threats to users and society, such as spreading fake news to manipulate public opinion in social media sites, amplifying unfairness toward under-represented groups or individuals in job matching services, or inferring privacy information from recommendation results. Therefore, systems' trustworthiness has been attracting increasing attention from various aspects for mitigating negative impacts caused by recommender systems, so as to enhance the public's trust towards recommender systems techniques. In this survey, we provide a comprehensive overview of Trustworthy Recommender systems (TRec) with a specific focus on six of the most important aspects; namely, Safety & Robustness, Nondiscrimination & Fairness, Explainability, Privacy, Environmental Well-being, and Accountability & Auditability. For each aspect, we summarize the recent related technologies and discuss potential research directions to help achieve trustworthy recommender systems in the future.
Paper Structure (90 sections, 7 equations, 3 figures, 9 tables)

This paper contains 90 sections, 7 equations, 3 figures, 9 tables.

Table of Contents

  1. Introduction
  2. Safety & Robustness
  3. Concepts and Taxonomy
  4. Attackers' Goal
  5. Attack Stage
  6. Attackers' Knowledge
  7. Adversarial Perturbation Type
  8. Countermeasure Strategies Against Adversarial Attacks (Defense Methods)
  9. Representative Attack Methods
  10. A Unified Formulation of Poisoning Attack.
  11. Heuristic Methods.
  12. Gradient-based Methods.
  13. Reinforcement Learning-based Methods.
  14. Representative Defense Methods
  15. Detection.
  16. ...and 75 more sections

Figures (3)

  • Figure 1: Six key dimensions of Trustworthy Recommender Systems (TRec).
  • Figure 2: The poisoning attack. Attackers inject well-designed faker users into training data to manipulate target model's behaviors.
  • Figure 8: Shadow training strategy in privacy attacks for recommender systems. The training process consists of two steps: training shadow recommendation models with public accessible auxiliary data and using the recommendation predictions to train the attacker.