Detecting Adversarial Attacks in the Context of Bayesian Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

Detecting Adversarial Attacks in the Context of Bayesian Networks

Emad Alsuwat
  • Function : Author
  • PersonId : 1059330
Hatim Alsuwat
  • Function : Author
  • PersonId : 1059331
John Rose
  • Function : Author
  • PersonId : 1059332
Marco Valtorta
  • Function : Author
  • PersonId : 1059333
Csilla Farkas
  • Function : Author
  • PersonId : 1016192


In this research, we study data poisoning attacks against Bayesian network structure learning algorithms. We propose to use the distance between Bayesian network models and the value of data conflict to detect data poisoning attacks. We propose a 2-layered framework that detects both one-step and long-duration data poisoning attacks. Layer 1 enforces “reject on negative impacts” detection; i.e., input that changes the Bayesian network model is labeled potentially malicious. Layer 2 aims to detect long-duration attacks; i.e., observations in the incoming data that conflict with the original Bayesian model. We show that for a typical small Bayesian network, only a few contaminated cases are needed to corrupt the learned structure. Our detection methods are effective against not only one-step attacks but also sophisticated long-duration attacks. We also present our empirical results.
Fichier principal
Vignette du fichier
480962_1_En_1_Chapter.pdf (766.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02384585 , version 1 (28-11-2019)





Emad Alsuwat, Hatim Alsuwat, John Rose, Marco Valtorta, Csilla Farkas. Detecting Adversarial Attacks in the Context of Bayesian Networks. 33th IFIP Annual Conference on Data and Applications Security and Privacy (DBSec), Jul 2019, Charleston, SC, United States. pp.3-22, ⟨10.1007/978-3-030-22479-0_1⟩. ⟨hal-02384585⟩
84 View
36 Download



Gmail Facebook X LinkedIn More