DREAM: Domain-free Reverse Engineering Attributes of Black-box Model

Rongqing Li, Jiaqi Yu, Changsheng Li, Wenhan Luo, Ye Yuan, Guoren Wang

Keywords: Model Attribute inference, domain-free method

Abstract: Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes (e.g., the number of convolutional layers) of a target black-box neural network can be exposed through a sequence of queries. There is a crucial limitation that these works assume the dataset used for training the target model to be known beforehand, and leverage this dataset for model attribute attack. However, it is difficult to access the training dataset of the target black-box model in reality. Therefore, whether the attributes of a target black-box model could be still revealed in this case is doubtful. In this paper, we investigate a new problem of Domain-free Reverse Engineering the Attributes of a black-box target Model, called DREAM, without requiring the model's training dataset available, and put forward a general and principled framework by casting this problem as an out of distribution (OOD) generalization problem. At the heart of our framework, we devise a multi-discriminator generative adversarial network (MDGAN) to learn domain invariant features. Based on these features, we can learn a domain-free model to inversely infer the attributes of a target black-box model with unknown training data. This makes our method one of the kinds that can gracefully apply to an arbitrary domain for model attribute reverse engineering with good generalization ability. Extensive experimental studies are conducted and the results validate the superiority of our proposed method over the baselines.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)