propinfer 1.0.1

Modular framework to run Property Inference Attacks on Machine Learning models.

Property Inference Attacks

In this repository, we propose a modular framework to run Property Inference Attacks on Machine Learning models.

Installation

You can get this package directly from pip or conda:

python -m pip install propinfer

Please note that PyTorch is required to run this framework. Please find installation instructions corresponding to you here.

Usage

This framework is made modular for any of your experiments: you simply should define subclasses of Generator and Model to represent your data source and your evaluated model respectively.

From these, you can create a specific experiment configuration file. We suggest using hydra for your configurations, but parameters can also be passed in a standard dict.

Alternatively, you can extend the Experiment class.

Threat models and attacks

White-Box

In this threat model, we have access to the model's parameters directly. In this case, [1] defines three different attacks:

• Simple meta-classifier attack
• Simple meta-classifier attack, with layer weights' sorting
• DeepSets attack

They are respectively designated by the keywords Naive, Sortand DeepSets.

Grey- and Black-Box

In this threat model, we have only query access to the model (we do not know its parameters). In the scope of the Grey-Box threat model, we know the model's architecture and hyperparameters - in the scope of Black-Box we do not.

For the Grey-Box case, [2] describes two simple attacks:

• The Loss Test (represented by the LossTest keyword)
• The Threshold Test (represented by the ThresholdTest keyword)

[3] also proposes a meta-classifier-based attack, that we use for both the Grey-Box and Black-Box cases: these are respectively represented by the GreyBox and BlackBox keywords. For the latter case, we simply default on a pre-defined model architecture.

Unit tests

The framework is provided with a few, simple unit tests. Run them with:

python -m unittest discover

to check the correctness of your installation.

References

[1] Karan Ganju, Qi Wang, Wei Yang, Carl A. Gunter, and Nikita Borisov. 2018. Property Inference Attacks on Fully Connected Neural Networks using Permutation Invariant Representations. In Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security (CCS '18). Association for Computing Machinery, New York, NY, USA, 619–633. DOI:https://doi.org/10.1145/3243734.3243834

[2] Anshuman Suri, David Evans. 2021. Formalizing Distribution Inference Risks. 2021 Workshop on Theory and Practice of Differential Privacy, ICML. https://arxiv.org/abs/2106.03699

[3] Wanrong Zhang, Shruti Tople, Olga Ohrimenko. 2021. Leakage of Dataset Properties in Multi-Party Machine Learning. https://arxiv.org/abs/2006.07267