MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation

High quality Machine Learning (ML) models are often considered valuable intellectual property by companies. Model Stealing (MS) attacks allow an adversary with blackbox access to a ML model to replicate its functionality by training a clone model using the predictions of the target model for different inputs. However, best available existing MS attacks fail to produce a high-accuracy clone without access to the target dataset or a representative dataset necessary to query the target model. In this paper, we show that preventing access to the target dataset is not an adequate defense to protect a model. We propose MAZE -a data-free model stealing attack using zeroth-order gradient estimation that produces high-accuracy clones. In contrast to prior works, MAZE uses only synthetic data created using a generative model to perform MS. Our evaluation with four image classification models shows that MAZE provides a normalized clone accuracy in the range of 0.90⇥ to 0.99⇥, and outperforms even the recent attacks that rely on partial data (JBDA, clone accuracy 0.13⇥ to 0.69⇥) and on surrogate data (KnockoffNets, clone accuracy 0.52⇥ to 0.97⇥). We also study an extension of MAZE in the partial-data setting, and develop MAZE-PD, which generates synthetic data closer to the target distribution. MAZE-PD further improves the clone accuracy (0.97⇥ to 1.0⇥) and reduces the query budget required for the attack by 2⇥-24⇥.