{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:33:30Z","timestamp":1763192010570,"version":"3.45.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229290","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs"],"prefix":"10.1109","author":[{"given":"Flint Xiaofeng","family":"Fan","sequence":"first","affiliation":[{"name":"Institute of High Performance Computing (IHPC) Agency for Science, Technology and Research,Centre for Frontier AI Research (CFAR),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheston","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC) Agency for Science, Technology and Research,Centre for Frontier AI Research (CFAR),Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roger","family":"Wattenhofer","sequence":"additional","affiliation":[{"name":"D-ITET ETH Zurich,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"CCDS, Nanyang Technological University,CFAR, IHPC, Agency for Science, Technology and Research,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240742"},{"article-title":"Action and trajectory planning for urban autonomous driving with hierarchical reinforcement learning","year":"2023","author":"Lu","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"article-title":"Semi-supervised knowledge transfer for deep learning from private training data","volume-title":"ICLR","author":"Papernot","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3270860"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41579-2_39"},{"key":"ref11","article-title":"Privacy-constrained policies via mutual information regularized policy gradients","author":"Cundy","year":"2024","journal-title":"AISTATS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"ref13","article-title":"Fault-tolerant federated reinforcement learning with theoretical guarantee","author":"Fan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Fedhql: Federated heterogeneous q-learning","year":"2023","author":"Fan","key":"ref14"},{"article-title":"The blessing of heterogeneity in federated q-learning: Linear speedup and beyond","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Woo","key":"ref15"},{"article-title":"Decentralized federated policy gradient with byzantine fault-tolerance and provably fast convergence","volume-title":"Proceedings of the 2024 International Conference on Autonomous Agents and Multiagent Systems","author":"Jordan","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3510352"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3682076"},{"article-title":"Federated offline reinforcement learning: Collaborative single-policy coverage suffices","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Woo","key":"ref19"},{"article-title":"Fedhpd: Heterogeneous federated reinforcement learning via policy distillation","year":"2025","author":"Jiang","key":"ref20"},{"volume-title":"Chatgpt","year":"2023","key":"ref21"},{"year":"2024","key":"ref22","article-title":"Deepseek-v3 technical report"},{"article-title":"Deep reinforcement learning from human preferences","volume-title":"Proceedings of NIPS","author":"Christiano","key":"ref23"},{"article-title":"Fine-tuning language models from human preferences","year":"2019","author":"Ziegler","key":"ref24"},{"article-title":"Learning to summarize with human feedback","volume-title":"Proceedings of NeurIPS","author":"Stiennon","key":"ref25"},{"article-title":"An llm-based recommender system environment","year":"2024","author":"Corecco","key":"ref26"},{"article-title":"Fedrlhf: A convergence-guaranteed federated framework for privacy-preserving and personalized rlhf","year":"2024","author":"Fan","key":"ref27"},{"article-title":"Cannot or should not? automatic analysis of refusal composition in ift\/rlhf datasets and refusal behavior of black-box llms","year":"2024","author":"von Recum","key":"ref28"},{"author":"Commission","key":"ref29","article-title":"General data protection regulation (gdpr)"},{"key":"ref30","article-title":"Health insurance portability and accountability act (hipaa)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1806689.1806787"},{"article-title":"Pan-private streaming algorithms","volume-title":"Proceedings of ICS","author":"Dwork","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2021"},{"article-title":"The price of differential privacy for online learning","volume-title":"Proceedings of ICML","author":"Agarwal","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390265"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"article-title":"Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","author":"Gilad-Bachrach","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978308"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"journal-title":"Apple Machine Learning Journal","article-title":"Learning with privacy at scale","year":"2017","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2018.00056"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref43","first-page":"2130","article-title":"Differentially private policy evaluation","volume-title":"International Conference on Machine Learning","author":"Balle"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3544837"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.4271\/j3216_202504"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2725339"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650755"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref49","article-title":"How you act tells a lot: Privacy-leaking attack on deep reinforcement learning","author":"Pan","year":"2019","journal-title":"AAMAS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992410"},{"article-title":"Private reinforcement learning with pac and regret guarantees","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Vietri","key":"ref51"},{"key":"ref52","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning","author":"Kakade"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.56"},{"article-title":"Extracting training data from large language models","volume-title":"USENIX Security Symposium","author":"Carlini","key":"ref54"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229290.pdf?arnumber=11229290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:30:22Z","timestamp":1763191822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229290","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}