{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:43:53Z","timestamp":1780357433039,"version":"3.54.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610832","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5148-5154","source":"Crossref","is-referenced-by-count":3,"title":["Privacy Risks in Reinforcement Learning for Household Robots"],"prefix":"10.1109","author":[{"given":"Miao","family":"Li","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA,15213"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Ding","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA,15213"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA,15213"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref4","author":"Brohan","year":"2023","journal-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390265"},{"key":"ref6","article-title":"Privacy-preserving q-learning with functional noise in continuous spaces","volume":"32","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106775"},{"key":"ref8","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Artificial intelligence and statistics","author":"McMahan","year":"2017"},{"key":"ref9","author":"Kone\u010dn\u1ef3","year":"2015","journal-title":"Federated optimization: Distributed optimization beyond the datacenter"},{"key":"ref10","author":"Kone\u010dn\u1ef3","year":"2016","journal-title":"Federated optimization: Distributed machine learning for on-device intelligence"},{"key":"ref11","author":"Reddi","year":"2020","journal-title":"Adaptive federated optimization"},{"key":"ref12","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume":"33","author":"Geiping","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00978"},{"key":"ref15","author":"Zhao","year":"2020","journal-title":"idlg: Improved deep leakage from gradients"},{"key":"ref16","first-page":"29898","article-title":"Gradient inversion with generative image prior","volume":"34","author":"Jeon","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01607"},{"key":"ref19","first-page":"368","article-title":"How you act tells a lot: Privacy-leaking attack on deep reinforcement learning","volume-title":"AAMAS","author":"Pan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"ref22","author":"Kolve","year":"2017","journal-title":"Ai2-thor: An interactive 3d environment for visual ai"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160946"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989164"},{"key":"ref26","author":"Rigaki","year":"2020","journal-title":"A survey of privacy attacks in machine learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref28","article-title":"Extracting training data from large language models","volume-title":"USENIX Security Symposium","volume":"6","author":"Carlini"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2022.24335"},{"key":"ref30","article-title":"Inceptionism: Going deeper into neural networks","author":"Mordvintsev","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref32","first-page":"994","article-title":"Cafe: Catastrophic data leakage in vertical federated learning","volume":"34","author":"Jin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.305"},{"key":"ref35","first-page":"9754","article-title":"Private reinforcement learning with pac and regret guarantees","volume-title":"International Conference on Machine Learning","author":"Vietri"},{"key":"ref36","first-page":"10561","article-title":"Local differential privacy for regret minimization in reinforcement learning","volume":"34","author":"Garcelon","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3576842.3582325"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"ref40","author":"Zhu","year":"2020","journal-title":"R-gap: Recursive gradient attack on privacy"},{"key":"ref41","first-page":"15884","article-title":"Cocktail party attack: Breaking aggregation-based privacy in federated learning using independent component analysis","volume-title":"International Conference on Machine Learning","author":"Kariyappa"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610832.pdf?arnumber=10610832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:22:00Z","timestamp":1723267320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610832","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}