Stealing Black-Box Functionality Using The Deep Neural Tree Architecture
Preprint
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
All Related Versions
This publication has 7 references indexed in Scilit:
- A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAIIEEE Transactions on Neural Networks and Learning Systems, 2020
- Knockoff Nets: Stealing Functionality of Black-Box Models2019
- Query-Efficient Black-Box Attack by Active Learning2018
- Stealing Hyperparameters in Machine Learning2018
- Membership Inference Attacks Against Machine Learning Models2017
- Practical Black-Box Attacks against Machine Learning2017
- Online active learning of decision trees with evidential dataPattern Recognition, 2016