Camouflage Learning. Sigg, S., Nguyen, L. N., & Ma, J. In The 19th International Conference on Pervasive Computing and Communications (PerCom 2021), adjunct, 2021. abstract bibtex Federated learning has been proposed as a concept for distributed machine learning which enforces privacy by avoiding sharing private data with a coordinator or distributed nodes. Instead of gathering datasets to a central server for model training in traditional machine learning, in federated learning, model updates are computed locally at distributed devices and merged at a coordinator. However, information on local data might be leaked through the model updates. We propose Camouflage learning, a distributed machine learning scheme that distributes both the data and the model. Neither the distributed devices nor the coordinator is at any point in time in possession of the complete model. Furthermore, data and model are obfuscated during distributed model inference and distributed model training. Camouflage learning can be implemented with various Machine learning schemes.
@inproceedings{Sigg2020Camouflage,
title={Camouflage Learning},
author={Stephan Sigg and Le Ngu Nguyen and Jing Ma},
booktitle={The 19th International Conference on Pervasive Computing and Communications (PerCom 2021), adjunct},
year={2021},
abstract={Federated learning has been proposed as a concept for distributed machine learning which enforces privacy by avoiding sharing private data with a coordinator or distributed nodes. Instead of gathering datasets to a central server for model training in traditional machine learning, in federated learning, model updates are computed locally at distributed devices and merged at a coordinator. However, information on local data might be leaked through the model updates. We propose Camouflage learning, a distributed machine learning scheme that distributes both the data and the model. Neither the distributed devices nor the coordinator is at any point in time in possession of the complete model. Furthermore, data and model are obfuscated during distributed model inference and distributed model training. Camouflage learning can be implemented with various Machine learning schemes.
},
group = {ambience},
project = {radiosense, abacus}
}
Downloads: 0
{"_id":"orbtigb2haP7EasXn","bibbaseid":"sigg-nguyen-ma-camouflagelearning-2021","authorIDs":["9sdTym9dh2BsmwNqn","mCkbNW7Xhuc8f4u7u"],"author_short":["Sigg, S.","Nguyen, L. N.","Ma, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Camouflage Learning","author":[{"firstnames":["Stephan"],"propositions":[],"lastnames":["Sigg"],"suffixes":[]},{"firstnames":["Le","Ngu"],"propositions":[],"lastnames":["Nguyen"],"suffixes":[]},{"firstnames":["Jing"],"propositions":[],"lastnames":["Ma"],"suffixes":[]}],"booktitle":"The 19th International Conference on Pervasive Computing and Communications (PerCom 2021), adjunct","year":"2021","abstract":"Federated learning has been proposed as a concept for distributed machine learning which enforces privacy by avoiding sharing private data with a coordinator or distributed nodes. Instead of gathering datasets to a central server for model training in traditional machine learning, in federated learning, model updates are computed locally at distributed devices and merged at a coordinator. However, information on local data might be leaked through the model updates. We propose Camouflage learning, a distributed machine learning scheme that distributes both the data and the model. Neither the distributed devices nor the coordinator is at any point in time in possession of the complete model. Furthermore, data and model are obfuscated during distributed model inference and distributed model training. Camouflage learning can be implemented with various Machine learning schemes. ","group":"ambience","project":"radiosense, abacus","bibtex":"@inproceedings{Sigg2020Camouflage,\n title={Camouflage Learning},\n author={Stephan Sigg and Le Ngu Nguyen and Jing Ma},\n booktitle={The 19th International Conference on Pervasive Computing and Communications (PerCom 2021), adjunct},\n year={2021},\n abstract={Federated learning has been proposed as a concept for distributed machine learning which enforces privacy by avoiding sharing private data with a coordinator or distributed nodes. Instead of gathering datasets to a central server for model training in traditional machine learning, in federated learning, model updates are computed locally at distributed devices and merged at a coordinator. However, information on local data might be leaked through the model updates. We propose Camouflage learning, a distributed machine learning scheme that distributes both the data and the model. Neither the distributed devices nor the coordinator is at any point in time in possession of the complete model. Furthermore, data and model are obfuscated during distributed model inference and distributed model training. Camouflage learning can be implemented with various Machine learning schemes.\n},\n group = {ambience},\n project = {radiosense, abacus}\n}\n\n","author_short":["Sigg, S.","Nguyen, L. N.","Ma, J."],"key":"Sigg2020Camouflage","id":"Sigg2020Camouflage","bibbaseid":"sigg-nguyen-ma-camouflagelearning-2021","role":"author","urls":{},"metadata":{"authorlinks":{"sigg, s":"https://thepreciousproject.eu/team_stephan.php","nguyen, l":"https://ambientintelligence.aalto.fi/team_le.php"}},"downloads":0},"bibtype":"inproceedings","biburl":"http://ambientintelligence.aalto.fi/bibtex/LiteraturAll","creationDate":"2021-01-18T08:57:08.802Z","downloads":0,"keywords":[],"search_terms":["camouflage","learning","sigg","nguyen","ma"],"title":"Camouflage Learning","year":2021,"dataSources":["aPfcTvMp5jE2KuS7H","a6QYyvmdLfrsx7DiL"]}