ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

Liu, Yugeng and Wen, Rui and He, Xinlei and Salem, Ahmed and Zhang, Zhikun and Backes, Michael and De Cristofaro, Emiliano and Fritz, Mario and Zhang, Yang
(2022) ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models.
In: USENIX Security Symposium (USENIX Security), 2022..
Conference: USENIX-Security Usenix Security Symposium
(In Press)

Full text not available from this repository.


Inference attacks against Machine Learning (ML) models allow adversaries to learn information about training data, model parameters, etc. While researchers have studied these attacks thoroughly, they have done so in isolation. We lack a comprehensive picture of the risks caused by the attacks, such as the different scenarios they can be applied to, the common factors that influence their performance, the relationship among them, or the effectiveness of defense techniques. In this paper, we fill this gap by presenting a first-of-its-kind holistic risk assessment of different inference attacks against machine learning models. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing - and establish a threat model taxonomy. Our extensive experimental evaluation conducted over five model architectures and four datasets shows that the complexity of the training dataset plays an important role with respect to the attack's performance, while the effectiveness of model stealing and membership inference attacks are negatively correlated. We also show that defenses like DP-SGD and Knowledge Distillation can only hope to mitigate some of the inference attacks. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models, and equally serves as a benchmark tool for researchers and practitioners.


Actions (login required)

View Item View Item