Ecole d'ingénieur et centre de recherche en Sciences du numérique

Security for distributed machine learning based software

Gomez, Laurent; Ibarrondo, Alberto; Wilhelm; Marquez, José; Duverger, Patrick

ICETE 2018, 15th International Joint Conference on E-Business and Telecommunications, 26-28 July 2018, Porto, Portugal / Also published as Part of the Communications in Computer and Information Science book series (CCIS, volume 1118)

Current developments in Enterprise Systems observe a paradigm shift, moving the needle from the backend to the edge sectors of those; by distributing data, decentralizing applications and integrating novel components seamlessly to the central systems. Distributively deployed AI capabilities will thrust this transition. Several non-functional requirements arise along with these developments, security being at the center of the discussions. Bearing those requirements in mind, hereby we propose an approach to holistically protect distributed Deep Neural Network (DNN) based/enhanced software assets, i.e. confidentiality of their input & output data streams as well as safeguarding their Intellectual Property. Making use of Fully Homomorphic Encryption (FHE), our approach enables the protection of Distributed Neural Networks, while processing encrypted data. On that respect we evaluate the feasibility of this solution on a Convolutional Neuronal Network (CNN) for image classification deployed on distributed infrastructures.

Doi Bibtex

Titre:Security for distributed machine learning based software
Mots Clés:Intellectual property protection, Fully homomorphic encryption neural networks, Distributed landscapes, Smart cities
Type:Conférence
Langue:English
Ville:Porto
Pays:PORTUGAL
Date:
Département:Sécurité numérique
Eurecom ref:6119
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in ICETE 2018, 15th International Joint Conference on E-Business and Telecommunications, 26-28 July 2018, Porto, Portugal / Also published as Part of the Communications in Computer and Information Science book series (CCIS, volume 1118) and is available at : https://doi.org/10.1007/978-3-030-34866-3_6
Bibtex: @inproceedings{EURECOM+6119, doi = {https://doi.org/10.1007/978-3-030-34866-3_6}, year = {2018}, title = {{S}ecurity for distributed machine learning based software}, author = {{G}omez, {L}aurent and {I}barrondo, {A}lberto and {W}ilhelm and {M}arquez, {J}os{\'e} and {D}uverger, {P}atrick}, booktitle = {{ICETE} 2018, 15th {I}nternational {J}oint {C}onference on {E}-{B}usiness and {T}elecommunications, 26-28 {J}uly 2018, {P}orto, {P}ortugal / {A}lso published as {P}art of the {C}ommunications in {C}omputer and {I}nformation {S}cience book series ({CCIS}, volume 1118)}, address = {{P}orto, {PORTUGAL}}, month = {07}, url = {http://www.eurecom.fr/publication/6119} }
Voir aussi: