mlsanityData to 7 Oct 2026

Unveiling Vulnerabilities of Contrastive Recommender Systems to Poisoning Attacks

arXiv 2311.18244 ↗First posted 30 Nov 2023cs.IR cs.CR cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Contrastive learning (CL) has recently gained prominence in the domain of recommender systems due to its great ability to enhance recommendation accuracy and improve model robustness. Despite its advantages, this paper identifies a vulnerability of CL-based recommender systems that they are more susceptible to poisoning attacks aiming to promote individual items. Our analysis indicates that this vulnerability is attributed to the uniform spread of representations caused by the InfoNCE loss. Furthermore, theoretical and empirical evidence shows that optimizing this loss favors smooth spectral values of representations. This finding suggests that attackers could facilitate this optimization process of CL by encouraging a more uniform distribution of spectral values, thereby enhancing the degree of representation dispersion. With these insights, we attempt to reveal a potential poisoning attack against CL-based recommender systems, which encompasses a dual-objective framework: one that induces a smoother spectral value distribution to amplify the InfoNCE loss's inherent dispersion effect, named dispersion promotion; and the other that directly elevates the visibility of target items, named rank promotion. We validate the threats of our attack model through extensive experimentation on four datasets. By shedding light on these vulnerabilities, our goal is to advance the development of more robust CL-based recommender systems. The code is available at urlhttps://github.com/CoderWZW/ARLib.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 39 of its 69 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

39 of 69 references.

References · 39

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  4. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  5. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  6. 2019Neural Graph Collaborative Filteringcited by 660
  7. 2017Generative Adversarial Networks: An Overviewcited by 588
  8. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  9. 2020Understanding the Behaviour of Contrastive Losscited by 397
  10. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  11. 2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
  12. 2020Self-supervised Graph Learning for Recommendationcited by 305
27 more
  1. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  2. 2021Contrastive Learning for Representation Degeneration Problem in Sequential Recommendationcited by 121
  3. 2022Self-Supervised Learning for Recommender Systems: A Surveycited by 95
  4. 2022Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learningcited by 86
  5. 2016Data Poisoning Attacks on Factorization-Based Collaborative Filteringcited by 78
  6. 2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 76
  7. 2022Towards Representation Alignment and Uniformity in Collaborative Filteringcited by 57
  8. 2022XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendationcited by 57
  9. 2018Poisoning Attacks to Graph-Based Recommender Systemscited by 52
  10. 2022Spectral Feature Augmentation for Graph Contrastive Learning and Beyondcited by 49
  11. 2021Self-Supervised Graph Co-Training for Session-based Recommendationcited by 43
  12. 2022Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrumcited by 43
  13. 2021PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotioncited by 37
  14. 2021Contrastive Learning Improves Model Robustness Under Label Noisecited by 36
  15. 2021Socially-Aware Self-Supervised Tri-Training for Recommendationcited by 32
  16. 2021Double-Scale Self-Supervised Hypergraph Learning for Group Recommendationcited by 32
  17. 2021Fast-adapting and Privacy-preserving Federated Recommender Systemcited by 30
  18. 2020Practical Data Poisoning Attack against Next-Item Recommendationcited by 27
  19. 2022CrossCBR: Cross-view Contrastive Learning for Bundle Recommendationcited by 26
  20. 2022Knowledge-enhanced Black-box Attacks for Recommendationscited by 25
  21. 2020Attacking Recommender Systems with Augmented User Profilescited by 24
  22. 2022Efficient Bi-Level Optimization for Recommendation Denoisingcited by 20
  23. 2022FedRecAttack: Model Poisoning Attack to Federated Recommendationcited by 18
  24. 2022A Review-aware Graph Contrastive Learning Framework for Recommendationcited by 18
  25. 2022Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarioscited by 13
  26. 2021Ready for Emerging Threats to Recommender Systems? A Graph Convolution-based Generative Shilling Attackcited by 10
  27. 2022UA-FedRec: Untargeted Attack on Federated News Recommendationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 6.

10 papers.

  1. 2024ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systemscited by 9
  2. 2025Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detectioncited by 3
  3. 2025SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systemscited by 2
  4. 2026PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation Detectioncited by 2
  5. 2025Relational Database Distillation: From Structured Tables to Condensed Graph Datacited by 1
  6. 2026DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendationcited by 0
  7. 2026Sharpness-Aware Poisoning: Enhancing Transferability of Injective Attacks on Recommender Systemscited by 0
  8. 2026Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attackscited by 0
  9. 2026An Efficient and Effective Agentic Group Shilling Attack on Recommender Systemscited by 0
  10. 2026VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agentscited by 0