PRADA: Protecting Against DNN Model Stealing Attacks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

255 Downloads (Pure)


Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model to find transferable adversarial examples that can evade classification by the original model. Access to the model can be restricted to be only via well-defined prediction APIs. Nevertheless, prediction APIs still provide enough information to allow an adversary to mount model extraction attacks by sending repeated queries via the prediction API. In this paper, we describe new model extraction attacks using novel approaches for generating synthetic queries, and optimizing training hyperparameters. Our attacks outperform state-of-the-art model extraction in terms of transferability of both targeted and non-targeted adversarial examples (up to +29-44 percentage points, pp), and prediction accuracy (up to +46 pp) on two datasets. We provide take-aways on how to perform effective model extraction attacks. We then propose PRADA, the first step towards generic and effective detection of DNN model extraction attacks. It analyzes the distribution of consecutive API queries and raises an alarm when this distribution deviates from benign behavior. We show that PRADA can detect all prior model extraction attacks with no false positives.
Original languageEnglish
Title of host publication IEEE European Symposium on Security and Privacy, EuroS&P 2019, Stockholm, Sweden, June 17-19, 2019
Number of pages16
ISBN (Electronic)978-1-7281-1148-3
Publication statusPublished - 2019
MoE publication typeA4 Article in a conference publication
EventIEEE European Symposium on Security and Privacy - Stockholm, Sweden
Duration: 17 Jun 201919 Jun 2019
Conference number: 4


ConferenceIEEE European Symposium on Security and Privacy
Abbreviated titleIEEE EuroS&P


  • Predictive models
  • Computational modeling
  • Training
  • Mathematical model
  • Data mining
  • Business
  • Neural networks
  • Adversarial machine learning
  • model extraction
  • model stealing
  • deep neural network


Dive into the research topics of 'PRADA: Protecting Against DNN Model Stealing Attacks'. Together they form a unique fingerprint.

Cite this