English

Stealing Black-Box Functionality Using The Deep Neural Tree Architecture

Machine Learning 2020-02-25 v1 Cryptography and Security Machine Learning

Abstract

This paper makes a substantial step towards cloning the functionality of black-box models by introducing a Machine learning (ML) architecture named Deep Neural Trees (DNTs). This new architecture can learn to separate different tasks of the black-box model, and clone its task-specific behavior. We propose to train the DNT using an active learning algorithm to obtain faster and more sample-efficient training. In contrast to prior work, we study a complex "victim" black-box model based solely on input-output interactions, while at the same time the attacker and the victim model may have completely different internal architectures. The attacker is a ML based algorithm whereas the victim is a generally unknown module, such as a multi-purpose digital chip, complex analog circuit, mechanical system, software logic or a hybrid of these. The trained DNT module not only can function as the attacked module, but also provides some level of explainability to the cloned model due to the tree-like nature of the proposed architecture.

Keywords

Cite

@article{arxiv.2002.09864,
  title  = {Stealing Black-Box Functionality Using The Deep Neural Tree Architecture},
  author = {Daniel Teitelman and Itay Naeh and Shie Mannor},
  journal= {arXiv preprint arXiv:2002.09864},
  year   = {2020}
}

Comments

8 pages, 7 figures, 1 table

R2 v1 2026-06-23T13:50:42.328Z