(2022) ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models.
|
Text
USENIXSECURITY22-MLDoctor.pdf Download (2MB) | Preview |
Abstract
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.
| Item Type: | Conference or Workshop Item (A Paper) (Paper) |
|---|---|
| Divisions: | Mario Fritz (MF) Michael Backes (InfSec) Yang Zhang (YZ) |
| Conference: | USENIX-Security Usenix Security Symposium |
| Depositing User: | Tobias Lorenz |
| Date Deposited: | 05 Oct 2021 09:46 |
| Last Modified: | 30 Jan 2023 12:24 |
| Primary Research Area: | NRA1: Trustworthy Information Processing |
| URI: | https://publications.cispa.saarland/id/eprint/3485 |
Actions
Actions (login required)
 |
View Item |