Shilling Recommender Systems by Generating Side-feature-aware Fake User Profiles
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917049886834688 |
|---|---|
| author | Wang, Yuanrong Du, Yingpeng |
| author_facet | Wang, Yuanrong Du, Yingpeng |
| contents | Recommender systems (RS) greatly influence users' consumption decisions, making them attractive targets for malicious shilling attacks that inject fake user profiles to manipulate recommendations. Existing shilling methods can generate effective and stealthy fake profiles when training data only contain rating matrix, but they lack comprehensive solutions for scenarios where side features are present and utilized by the recommender. To address this gap, we extend the Leg-UP framework by enhancing the generator architecture to incorporate side features, enabling the generation of side-feature-aware fake user profiles. Experiments on benchmarks show that our method achieves strong attack performance while maintaining stealthiness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Shilling Recommender Systems by Generating Side-feature-aware Fake User Profiles Wang, Yuanrong Du, Yingpeng Information Retrieval Machine Learning Recommender systems (RS) greatly influence users' consumption decisions, making them attractive targets for malicious shilling attacks that inject fake user profiles to manipulate recommendations. Existing shilling methods can generate effective and stealthy fake profiles when training data only contain rating matrix, but they lack comprehensive solutions for scenarios where side features are present and utilized by the recommender. To address this gap, we extend the Leg-UP framework by enhancing the generator architecture to incorporate side features, enabling the generation of side-feature-aware fake user profiles. Experiments on benchmarks show that our method achieves strong attack performance while maintaining stealthiness. |
| title | Shilling Recommender Systems by Generating Side-feature-aware Fake User Profiles |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2509.17918 |