Awesome robust graph-based recommendation system Papers

This repository aims to provide links to work about adversarial robustness and privacy security on the Graph-based recommendation system.

Contents

• 1. Survey Papers
• 2. Graph-based recommendation system Papers
• 3. Adversarial robustness Papers
  • 3.1 White-box Attack & Grey-box Attack
  • 3.2 Blak-box-attack
  • 3.3 Adversarial robustness defend
  • 3.4 Graph purification
  • 3.5 Graph-based recommendation system robustness evaluation
• 4. Privacy attack on Graph-based recommendation system Papers
• 5. Differential privacy on Graph-based recommendation system Papers
• 6. Federated learning on Graph-based recommendation system Papers

0. Toolbox

Github Repository: DeepRobust (https://github.com/DSE-MSU/DeepRobust)

Corresponding paper: DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses. [paper][documentation]

1. Survey Papers

1. Adversarial Attacks and Defenses on Graphs: A Review and Empirical Study. SIGKDD Explorations 2020. [paper] [code]
2. A Comprehensive Survey on Trustworthy Recommender Systems. WWW, Tutorial 2023. [paper] [tutorial]
3. Adversarial attack and defense on graph data: A survey. IEEE Transactions on Knowledge and Data Engineering, 2022. [paper]

2. Graph-based recommendation system Papers

1. Inductive Representation Learning on Large Graphs SIGIR 2017. [paper] [code]
2. Lightgcn: Simplifying and powering graph convolution network for recommendation. SIGIR 2020. [paper] [code]

3. Adversarial robustness Papers

3.1 White-box Attack & Grey-box Attack

1. Poisoning attacks to graph-based recommender systems. ACSAC 2018. [paper]
2. Adversarial attacks on neural networks for graph data. KDD 2018. [paper] [code]
3. Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation. ICLR 2021. [paper] [code]
4. Revisiting Item Promotion in GNN-Based Collaborative Filtering: A Masked Targeted Topological Attack Perspective. AAAI 2023. [paper]
5. Targeted Shilling Attacks on GNN-based Recommender Systems. CIKM 2023 [paper]

3.2 Blackbox Attack

1. An Adaptive Data Poisoning Framework for Attacking Black-box Recommender Systems. ICDE 2020. [paper]
2. Knowledge-enhanced Black-box Attacks for Recommendations. KDD 2022. [paper] [slide]
3. Debiasing Learning for Membership Inference Attacks Against Recommender Systems. KDD 2022. [paper] [code]
4. Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy. SecureComm 2022. [paper]
5. Poisoning GNN-based Recommender Systems with Generative Surrogate-based Attacks. ACM TIS [paper]

3.3 Adversarial robustness defend

1. Gcn-based user representation learning for unifying robust recommendation and fraudster detection. SIGIR 2020 [paper] [code]
2. Adversarial graph perturbations for recommendations at scale. SIGIR 2022 [paper]
3. Anti-FakeU: Defending Shilling Attacks on Graph Neural Network based Recommender Model. www 2023 [paper]
4. On the Vulnerability of Graph Learning based Collaborative Filtering. ACM Transactions on Information Systems [paper]
5. Data Poisoning Attacks on Graph Convolutional Matrix Completion. ICA3PP 2019 [paper])

3.4 Graph purification

1. FRAUDRE: Fraud Detection Dual-Resistant to Graph Inconsistency and Imbalance. ICDM 2021 [paper] [code]

3.5 Graph-based recommendation system robustness evaluation

1. Robust Preference-Guided Denoising for Graph-based Social Recommendation. WWW 2023 [paper] [code]

4. Privacy attack on Graph-based recommendation system Papers

1. Graph embedding for recommendation against attribute inference attacks. WWW 2021. [paper]
2. Black-box attacks on sequential recommenders via data-free model extraction. RecSys 2021. [paper] [code]
3. Membership Inference Attacks Against Robust Graph Neural Network. CSS 2022 [paper]

5. Differential privacy on Graph-based recommendation system Papers

1. Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks.[paper]
2. Heterogeneous graph neural network for privacy-preserving recommendation. ICDM 2022. [paper] [code]

6. Federated learning on Graph-based recommendation system Papers

1. Heterogeneous graph neural network for privacy-preserving recommendation. ICML 2023. [paper] [code]