GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2020

GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning


Embedded systems demand on-device processing of data using Neural Networks (NNs) while conforming to the memory, power and computation constraints, leading to an efficiency and accuracy tradeoff. To bring NNs to edge devices, several optimizations such as model compression through pruning, quantization, and off-the-shelf architectures with efficient design have been extensively adopted. These algorithms when deployed to real world sensitive applications, requires to resist inference attacks to protect privacy of users training data. However, resistance against inference attacks is not accounted for designing NN models for IoT. In this work, we analyse the three-dimensional privacy-accuracy-efficiency tradeoff in NNs for IoT devices and propose Gecko training methodology where we explicitly add resistance to private inferences as a design objective. We optimize the inference-time memory, computation, and power constraints of embedded devices as a criterion for designing NN architecture while also preserving privacy. We choose quantization as design choice for highly efficient and private models. This choice is driven by the observation that compressed models leak more information compared to baseline models while off-the-shelf efficient architectures indicate poor efficiency and privacy tradeoff. We show that models trained using Gecko methodology are comparable to prior defences against black-box membership attacks in terms of accuracy and privacy while providing efficiency.
Fichier principal
Vignette du fichier
paper.pdf (508.54 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02958323 , version 1 (05-10-2020)


  • HAL Id : hal-02958323 , version 1


Vasisht Duddu, Antoine Boutet, Virat Shejwalkar. GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning. 2020. ⟨hal-02958323⟩
40 View
113 Download


Gmail Facebook X LinkedIn More