{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T15:30:53Z","timestamp":1775662253512,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"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":[[2025,9,8]]},"DOI":"10.1109\/cns66487.2025.11194960","type":"proceedings-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T17:34:49Z","timestamp":1760549689000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Fission: Distributed Privacy-Preserving Large Language Model Inference"],"prefix":"10.1109","author":[{"given":"Mehmet","family":"Ugurbil","sequence":"first","affiliation":[{"name":"Nillion"}]},{"given":"Dimitris","family":"Mouris","sequence":"additional","affiliation":[{"name":"Nillion"}]},{"given":"Manuel B.","family":"Santos","sequence":"additional","affiliation":[{"name":"Nillion"}]},{"given":"Jos\u00e9","family":"Cabrero-Holgueras","sequence":"additional","affiliation":[{"name":"Nillion"}]},{"given":"Miguel","family":"de Vega","sequence":"additional","affiliation":[{"name":"Nillion"}]},{"given":"Shubho","family":"Sengupta","sequence":"additional","affiliation":[{"name":"Meta"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"ref3","article-title":"The Llama 3 Herd of Models","author":"Grattafiori","year":"2024","journal-title":"arXiv"},{"key":"ref4","author":"Radford","year":"2019","journal-title":"Language Models are Unsupervised Multitask Learn-ers"},{"key":"ref5","author":"Black","year":"2021","journal-title":"GPT-Neo: Large Scale Autoregressive Language Mod-eling with Mesh-Tensorflow"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3575792"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-75757-0_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2024-0107"},{"key":"ref10","article-title":"Curl: Private LLMs through Wavelet-Encoded Look-Up Tables","author":"Santos","year":"2024","journal-title":"CAMLIS"},{"key":"ref11","first-page":"4961","article-title":"Crypten: Secure multi-party computation meets machine learning","volume":"34","author":"Knott","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","first-page":"1","article-title":"MPCFormer: Fast, performant and private transformer inference with MPC","author":"Li","year":"2023","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359824"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3485259"},{"key":"ref15","first-page":"51 904","article-title":"Bounding the invertibility of privacy-preserving in-stance encoding using fisher information","volume":"36","author":"Maeng","year":"2023","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/date64628.2025.10992988"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS55109.2022.00025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.790"},{"key":"ref19","article-title":"Puma: Secure inference of llama\u2212 7b in five minutes","author":"Dong","year":"2023","journal-title":"arXiv"},{"key":"ref20","first-page":"17","article-title":"SecretFlow-SPU: A performant and User-Friendly frame-work for Privacy-Preserving machine learning","volume-title":"USENIX ATC 23","author":"Ma","year":"2023"},{"key":"ref21","author":"Vepakomma","year":"2018","journal-title":"Split learning for health: Distributed deep learning without sharing raw patient data"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384740"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICMC60390.2024.00008"},{"key":"ref24","article-title":"Submix: Practical private prediction for large-scale language models","author":"Ginart","year":"2022","journal-title":"arXiv"},{"key":"ref25","article-title":"Split-and-denoise: protect large language model inference with local differential privacy","author":"Mai","year":"2024","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3559613.3563201"},{"key":"ref27","author":"Qiu","year":"2023","journal-title":"Evaluating privacy leakage in split learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690295"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.765"},{"key":"ref30","article-title":"Interpretable complex-valued neural networks for privacy protection","author":"Xiang","year":"2019","journal-title":"arXiv"},{"key":"ref31","author":"Yuan","year":"2023","journal-title":"Secure transformer inference proto-col"},{"key":"ref32","article-title":"PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN","author":"Zheng","year":"2024","journal-title":"arXiv"},{"key":"ref33","first-page":"160","article-title":"Protocols for secure computations (extended abstract)","volume-title":"23rd FOCS","author":"Yao","year":"1982"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46766-1_34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00342633"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2034691.2034742"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3022358"},{"key":"ref38","article-title":"Unveiling the unseen: Exploring whitebox membership inference through the lens of explainability","author":"Li","year":"2024","journal-title":"arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64840-4_12"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2024-0040"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/Trustcom.2015.357"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"}],"event":{"name":"2025 IEEE Conference on Communications and Network Security (CNS)","location":"Avignon, France","start":{"date-parts":[[2025,9,8]]},"end":{"date-parts":[[2025,9,11]]}},"container-title":["2025 IEEE Conference on Communications and Network Security (CNS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11194903\/11194169\/11194960.pdf?arnumber=11194960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T04:49:18Z","timestamp":1760590158000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11194960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/cns66487.2025.11194960","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]}}}