# Information Laundering for Model Privacy

arXiv: https://arxiv.org/abs/2009.06112 · HTML: https://mlsanity.com/paper/2009.06112/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2020.

## Built on by (most cited first, 13 of 13)

- [I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences](https://mlsanity.com/paper/2206.08451/) (2022)
- [Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack](https://mlsanity.com/paper/2105.00623/) (2021)
- [Federated Learning Challenges and Opportunities: An Outlook](https://mlsanity.com/paper/2202.00807/) (2022)
- [Self-Aware Personalized Federated Learning](https://mlsanity.com/paper/2204.08069/) (2022)
- [Model Stealing for Any Low-Rank Language Model](https://mlsanity.com/paper/2411.07536/) (2024)
- [GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations](https://mlsanity.com/paper/2106.01425/) (2021)
- [Adversarial Sampling for Fairness Testing in Deep Neural Network](https://mlsanity.com/paper/2303.02874/) (2023)
- [A Framework for Incentivized Collaborative Learning](https://mlsanity.com/paper/2305.17052/) (2023)
- [Model Privacy: A Unified Framework for Understanding Model Stealing Attacks and Defenses](https://mlsanity.com/paper/2502.15567/) (2025)
- [Decentralized Multi-Target Cross-Domain Recommendation for Multi-Organization Collaborations](https://mlsanity.com/paper/2110.13340/) (2021)
- [A Framework for Understanding Model Extraction Attack and Defense](https://mlsanity.com/paper/2206.11480/) (2022)
- [Regulating Clients' Noise Adding in Federated Learning without Verification](https://mlsanity.com/paper/2302.12735/) (2023)
- [Randomized Kaczmarz in Adversarial Distributed Setting](https://mlsanity.com/paper/2302.14615/) (2023)

## Abstract (arXiv)

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be deployed for public use. The private model can be obtained from general learning methods, and its deployment means that it will return a deterministic or random response for a given input query. An information-laundered model consists of probabilistic components that deliberately maneuver the intended input and output for queries to the model, so the model's adversarial acquisition is less likely. Under the proposed framework, we develop an information-theoretic principle to quantify the fundamental tradeoffs between model utility and privacy leakage and derive the optimal design.