Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement Paradigm
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_ | 1866915689548218368 |
|---|---|
| author | Su, Jiajie Nan, Zihan Ma, Yunshan Xia, Xiaobo Feng, Xiaohua Liu, Weiming Chen, Xiang Zheng, Xiaolin Chen, Chaochao |
| author_facet | Su, Jiajie Nan, Zihan Ma, Yunshan Xia, Xiaobo Feng, Xiaohua Liu, Weiming Chen, Xiang Zheng, Xiaolin Chen, Chaochao |
| contents | Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles thus lacking practicality. In this paper, we focus on the Profile Pollution Attack that subtly contaminates partial user interactions to induce targeted mispredictions. Previous PPA methods suffer from two limitations, i.e., i) over-reliance on sequence horizon impact restricts fine-grained perturbations on item transitions, and ii) holistic modifications cause detectable distribution shifts. To address these challenges, we propose a constrained reinforcement driven attack CREAT that synergizes a bi-level optimization framework with multi-reward reinforcement learning to balance adversarial efficacy and stealthiness. We first develop a Pattern Balanced Rewarding Policy, which integrates pattern inversion rewards to invert critical patterns and distribution consistency rewards to minimize detectable shifts via unbalanced co-optimal transport. Then we employ a Constrained Group Relative Reinforcement Learning paradigm, enabling step-wise perturbations through dynamic barrier constraints and group-shared experience replay, achieving targeted pollution with minimal detectability. Extensive experiments demonstrate the effectiveness of CREAT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09392 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement Paradigm Su, Jiajie Nan, Zihan Ma, Yunshan Xia, Xiaobo Feng, Xiaohua Liu, Weiming Chen, Xiang Zheng, Xiaolin Chen, Chaochao Machine Learning Artificial Intelligence Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles thus lacking practicality. In this paper, we focus on the Profile Pollution Attack that subtly contaminates partial user interactions to induce targeted mispredictions. Previous PPA methods suffer from two limitations, i.e., i) over-reliance on sequence horizon impact restricts fine-grained perturbations on item transitions, and ii) holistic modifications cause detectable distribution shifts. To address these challenges, we propose a constrained reinforcement driven attack CREAT that synergizes a bi-level optimization framework with multi-reward reinforcement learning to balance adversarial efficacy and stealthiness. We first develop a Pattern Balanced Rewarding Policy, which integrates pattern inversion rewards to invert critical patterns and distribution consistency rewards to minimize detectable shifts via unbalanced co-optimal transport. Then we employ a Constrained Group Relative Reinforcement Learning paradigm, enabling step-wise perturbations through dynamic barrier constraints and group-shared experience replay, achieving targeted pollution with minimal detectability. Extensive experiments demonstrate the effectiveness of CREAT. |
| title | Potent but Stealthy: Rethink Profile Pollution against Sequential Recommendation via Bi-level Constrained Reinforcement Paradigm |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.09392 |