mlsanityData to 7 Oct 2026

Stealthy Attack on Large Language Model based Recommendation

arXiv 2402.14836 ↗First posted 18 Feb 2024cs.CL cs.AI cs.IRcited by 19

Not on the map. Why?

Abstract (arXiv)

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely overlooked. In this work, we reveal that the introduction of LLMs into recommendation models presents new security vulnerabilities due to their emphasis on the textual content of items. We demonstrate that attackers can significantly boost an item's exposure by merely altering its textual content during the testing phase, without requiring direct interference with the model's training process. Additionally, the attack is notably stealthy, as it does not affect the overall recommendation performance and the modifications to the text are subtle, making it difficult for users and platforms to detect. Our comprehensive experiments across four mainstream LLM-based recommendation models demonstrate the superior efficacy and stealthiness of our approach. Our work unveils a significant security gap in LLM-based recommendation systems and paves the way for future research on protecting these systems.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 41 of its 55 references that are in the map. First posted on arXiv 18 Feb 2024.

Builds on

41 of 55 references.

References · 41

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2020Longformer: The Long-Document Transformercited by 3,362
  3. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  4. 2015Image-based Recommendations on Styles and Substitutescited by 702
  5. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  6. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
  7. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  8. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 396
  9. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  10. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 336
  11. 2023Large Language Models are Zero-Shot Rankers for Recommender Systemscited by 307
  12. 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 192
29 more
  1. 2023Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approachcited by 168
  2. 2023Uncovering ChatGPT's Capabilities in Recommender Systemscited by 160
  3. 2022M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systemscited by 152
  4. 2023Text Is All You Need: Learning Language Representations for Sequential Recommendationcited by 149
  5. 2023How Can Recommender Systems Benefit from Large Language Models: A Surveycited by 141
  6. 2023Tensor Trust: Interpretable Prompt Injection Attacks from an Online Gamecited by 135
  7. 2023Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisitedcited by 124
  8. 2022Towards Universal Sequence Representation Learning for Recommender Systemscited by 120
  9. 2021Causal Intervention for Leveraging Popularity Bias in Recommendationcited by 116
  10. 2023Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Predictioncited by 113
  11. 2022Learning Vector-Quantized Item Representation for Transferable Sequential Recommenderscited by 112
  12. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 99
  13. 2022Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learningcited by 85
  14. 2021Mining Latent Structures for Multimedia Recommendationcited by 79
  15. 2016Data Poisoning Attacks on Factorization-Based Collaborative Filteringcited by 78
  16. 2020Influence Function based Data Poisoning Attacks to Top-N Recommender Systemscited by 61
  17. 2018Poisoning Attacks to Graph-Based Recommender Systemscited by 52
  18. 2021Data Poisoning Attacks to Deep Learning Based Recommender Systemscited by 41
  19. 2023E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendationcited by 39
  20. 2023Large Language Model Augmented Narrative Driven Recommendationscited by 31
  21. 2020Practical Data Poisoning Attack against Next-Item Recommendationcited by 27
  22. 2020Attacking Recommender Systems with Augmented User Profilescited by 24
  23. 2021Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendationcited by 18
  24. 2022Shilling Black-box Recommender Systems by Learning to Generate Fake User Profilescited by 15
  25. 2024Poisoning Attacks against Recommender Systems: A Surveycited by 7
  26. 2023Mining Stable Preferences: Adaptive Modality Decorrelation for Multimedia Recommendationcited by 5
  27. 2019Assessing the Impact of a User-Item Collaborative Attack on Class of Userscited by 3
  28. 2022Targeted Data Poisoning Attack on News Recommendation System by Content Perturbationcited by 2
  29. 2023Collaborative Word-based Pre-trained Item Representation for Transferable Recommendationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 8; 2026: 5.

19 papers.

Sort:

By area:

  1. 2024Knowledge Graph Enhanced Large Language Model Editingcited by 38
  2. 2025A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigmscited by 17
  3. 2025DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agentscited by 12
  4. 2024Efficient Inference for Large Language Model-based Generative Recommendationcited by 11
  5. 2025StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimizationcited by 10
  6. 2024ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systemscited by 9
  7. 2025Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimizationcited by 8
  8. 2024CoRA: Collaborative Information Perception by Large Language Model's Weights for Recommendationcited by 7
  9. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
  10. 2024Modality-Balanced Learning for Multimedia Recommendationcited by 5
  11. 2025Preserving Privacy and Utility in LLM-Based Product Recommendationscited by 5
  12. 2025Exploring Backdoor Attack and Defense for LLM-empowered Recommendationscited by 4
7 more
  1. 2025Retrieval-Augmented Review Generation for Poisoning Recommender Systemscited by 3
  2. 2026Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankerscited by 3
  3. 2026Controlling Output Rankings in Generative Engines for LLM-based Searchcited by 3
  4. 2024Privacy in LLM-based Recommendation: Recent Advances and Future Directionscited by 2
  5. 2026Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attackscited by 0
  6. 2026Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivitycited by 0
  7. 2026VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agentscited by 0