# Dissecting Distribution Inference

Source: [Dissecting Distribution Inference](<https://www.sota2.com/research/paper/68fa72d61e209131cea58d0b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:35:49.064Z

Authors: Anshuman Suri, Yifu Lu, Yanjin Chen, David Evans

Published: 2022-12-15T02:43:51.000Z

## Abstract

A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well understood and demonstrated attacks often rely on strong and unrealistic assumptions such as full knowledge of training environments even in supposedly black-box threat scenarios. To improve understanding of distribution inference risks, we develop a new black-box attack that even outperforms the best known white-box attack in most settings. Using this new attack, we evaluate distribution inference risk while relaxing a variety of assumptions about the adversary's knowledge under black-box access, like known model architectures and label-only access. Finally, we evaluate the effectiveness of previously proposed defenses and introduce new defenses. We find that although noise-based defenses appear to be ineffective, a simple re-sampling defense can be highly effective. Code is available at https://github.com/iamgroot42/dissecting\_distribution\_inference

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [CC on ChatDoctor](<https://www.sota2.com/research/sota/cc-on-chatdoctor.md>): CC; ChatDoctor; MAE: 0.0304.

- [CC on MedCalc](<https://www.sota2.com/research/sota/cc-on-medcalc.md>): CC; MedCalc; MAE: 0.0104.

- [Property Inference Defense on MedCalc CC](<https://www.sota2.com/research/sota/property-inference-defense-on-medcalc-cc.md>): Property Inference Defense; MedCalc CC; Generation Attack MAE: 0.0153.

- [QA (MAE) on ChatDoctor](<https://www.sota2.com/research/sota/qa-mae-on-chatdoctor.md>): QA; ChatDoctor; MAE: 0.1271.

- [Property Inference Defense on MedCalc QA](<https://www.sota2.com/research/sota/property-inference-defense-on-medcalc-qa.md>): Property Inference Defense; MedCalc QA; Generation Attack MAE: 0.2065.

- [Property Inference Defense on ChatDoctor CC](<https://www.sota2.com/research/sota/property-inference-defense-on-chatdoctor-cc.md>): Property Inference Defense; ChatDoctor CC; Generation Attack MAE: 0.1392.

- [QA on MedCalc](<https://www.sota2.com/research/sota/qa-on-medcalc.md>): QA; MedCalc; MAE: 0.2065.

- [Property Inference Defense on ChatDoctor QA](<https://www.sota2.com/research/sota/property-inference-defense-on-chatdoctor-qa.md>): Property Inference Defense; ChatDoctor QA; Generation Attack MAE: 0.1853.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.07591>)

[PDF](<https://arxiv.org/pdf/2212.07591.pdf>)
