Reconstruction attack through classifier analysis - Data and Applications Security and Privacy XXVI Access content directly
Conference Papers Year : 2012

Reconstruction attack through classifier analysis

Abstract

In this paper, we introduce a novel inference attack that we coin as the reconstruction attack whose objective is to reconstruct a probabilistic version of the original dataset on which a classifier was learnt from the description of this classifier and possibly some auxiliary information. In a nutshell, the reconstruction attack exploits the structure of the classifier in order to derive a probabilistic version of dataset on which this model has been trained. Moreover, we propose a general framework that can be used to assess the success of a reconstruction attack in terms of a novel distance between the reconstructed and original datasets. In case of multiple releases of classifiers, we also give a strategy that can be used to merge the different reconstructed datasets into a single coherent one that is closer to the original dataset than any of the simple reconstructed datasets. Finally, we give an instantiation of this reconstruction attack on a decision tree classifier that was learnt using the algorithm C4.5 and evaluate experimentally its efficiency. The results of this experimentation demonstrate that the proposed attack is able to reconstruct a significant part of the original dataset, thus highlighting the need to develop new learning algorithms whose output is specifically tailored to mitigate the success of this type of attack.
Fichier principal
Vignette du fichier
978-3-642-31540-4_21_Chapter.pdf (262.74 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00736945 , version 1 (08-06-2017)

Licence

Attribution

Identifiers

Cite

Sébastien Gambs, Ahmed Gmati, Michel Hurfin. Reconstruction attack through classifier analysis. 26th Conference on Data and Applications Security and Privacy (DBSec), Jul 2012, Paris, France. pp.274-281, ⟨10.1007/978-3-642-31540-4_21⟩. ⟨hal-00736945⟩
894 View
330 Download

Altmetric

Share

Gmail Facebook X LinkedIn More