# Private Training Set Inspection in MLaaS

arXiv: https://arxiv.org/abs/2305.09058 · HTML: https://mlsanity.com/paper/2305.09058/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 16 of 16)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [White-box vs Black-box: Bayes Optimal Strategies for Membership Inference](https://mlsanity.com/paper/1908.11229/) (2019)
- [Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference](https://mlsanity.com/paper/1906.11798/) (2019)
- [Dataset Inference: Ownership Resolution in Machine Learning](https://mlsanity.com/paper/2104.10706/) (2021)
- [The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Services](https://mlsanity.com/paper/1905.07082/) (2019)
- [Privacy Enhanced Multimodal Neural Representations for Emotion Recognition](https://mlsanity.com/paper/1910.13212/) (2019)
- [Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model's Complexity](https://mlsanity.com/paper/2104.13061/) (2021)
- [Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning](https://mlsanity.com/paper/1805.05838/) (2018)
- [Provenance Data in the Machine Learning Lifecycle in Computational Science and Engineering](https://mlsanity.com/paper/1910.04223/) (2019)
- [Correlation inference attacks against machine learning models](https://mlsanity.com/paper/2112.08806/) (2021)
- [Formalizing Distribution Inference Risks](https://mlsanity.com/paper/2106.03699/) (2021)
- [Data Origin Inference in Machine Learning](https://mlsanity.com/paper/2211.13416/) (2022)

## Abstract (arXiv)

Machine Learning as a Service (MLaaS) is a popular cloud-based solution for customers who aim to use an ML model but lack training data, computation resources, or expertise in ML. In this case, the training datasets are typically a private possession of the ML or data companies and are inaccessible to the customers, but the customers still need an approach to confirm that the training datasets meet their expectations and fulfil regulatory measures like fairness. However, no existing work addresses the above customers' concerns. This work is the first attempt to solve this problem, taking data origin as an entry point. We first define origin membership measurement and based on this, we then define diversity and fairness metrics to address customers' concerns. We then propose a strategy to estimate the values of these two metrics in the inaccessible training dataset, combining shadow training techniques from membership inference and an efficient featurization scheme in multiple instance learning. The evaluation contains an application of text review polarity classification applications based on the language BERT model. Experimental results show that our solution can achieve up to 0.87 accuracy for membership inspection and up to 99.3% confidence in inspecting diversity and fairness distribution.