Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908412331163648 |
|---|---|
| author | Fan, Flint Xiaofeng Tan, Cheston Wattenhofer, Roger Ong, Yew-Soon |
| author_facet | Fan, Flint Xiaofeng Tan, Cheston Wattenhofer, Roger Ong, Yew-Soon |
| contents | The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential decision-making systems where sensitive information emerges from temporal patterns, behavioral strategies, and collaborative dynamics. Modern RL paradigms, such as federated RL (FedRL) and RL with human feedback (RLHF) in large language models (LLMs), exacerbate these challenges by introducing complex, interactive, and context-dependent learning environments that traditional methods do not address. In this position paper, we argue for a new privacy paradigm built on four core principles: multi-scale protection, behavioral pattern protection, collaborative privacy preservation, and context-aware adaptation. These principles expose inherent tensions between privacy, utility, and interpretability that must be navigated as RL systems become more pervasive in high-stakes domains like healthcare, autonomous vehicles, and decision support systems powered by LLMs. To tackle these challenges, we call for the development of new theoretical frameworks, practical mechanisms, and rigorous evaluation methodologies that collectively enable effective privacy protection in sequential decision-making systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11511 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs Fan, Flint Xiaofeng Tan, Cheston Wattenhofer, Roger Ong, Yew-Soon Machine Learning Artificial Intelligence The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential decision-making systems where sensitive information emerges from temporal patterns, behavioral strategies, and collaborative dynamics. Modern RL paradigms, such as federated RL (FedRL) and RL with human feedback (RLHF) in large language models (LLMs), exacerbate these challenges by introducing complex, interactive, and context-dependent learning environments that traditional methods do not address. In this position paper, we argue for a new privacy paradigm built on four core principles: multi-scale protection, behavioral pattern protection, collaborative privacy preservation, and context-aware adaptation. These principles expose inherent tensions between privacy, utility, and interpretability that must be navigated as RL systems become more pervasive in high-stakes domains like healthcare, autonomous vehicles, and decision support systems powered by LLMs. To tackle these challenges, we call for the development of new theoretical frameworks, practical mechanisms, and rigorous evaluation methodologies that collectively enable effective privacy protection in sequential decision-making systems. |
| title | Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.11511 |