AI ethics evidence index Search
Source-linked daily record
Evidence record 3307 · automatically gathered

Fair Finetuning Mitigates Distribution Inference Attacks

Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference attack (DIA). An adversary with black-box access can infer sensitive demographic properties, such as subgroup proportions, without observing any training data directly. While defenses such as differential privacy and property unlearning have been proposed, the link between fairness constraints and distributional leaka

Record details

Published: 1 June 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Privacy
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Same publisher byline · Shared topic: Bias & fairness

Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning

arXiv cs.CR (AI security) · 18 July 2026

Same publisher byline · Shared topic: Bias & fairness

Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning

arXiv cs.CY · 21 July 2026

Shared topic: Bias & fairness · Shared topic: Privacy

Silent Failures in Federated Personalization of Foundation Models

arXiv · 31 May 2026

Shared topic: Bias & fairness · Shared topic: Privacy

Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems

arXiv · 23 May 2026

Shared topic: Bias & fairness · Shared topic: Privacy

Democracy in the Era of Artificial Intelligence

arXiv · 11 June 2026

Shared topic: Bias & fairness · Shared topic: Privacy

What is ethical: AIHED driving humans or Human-Driven AIHED? A conceptual framework enabling the ‘ethos’ of AI-driven higher education

OpenAlex · 19 May 2026

How to cite this record

ethics.ai (1 June 2026), “Fair Finetuning Mitigates Distribution Inference Attacks,” evidence record 3307, https://ethics.ai/record/3307 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.