AI ethics evidence index Search
Source-linked daily record
Evidence record 12244 · automatically gathered

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

Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems. Prior work has shown that DP-SGD can widen accuracy disparities across demographic groups, but this framing treats fairness as a purely outcome-side concern. We argue that privacy cost, the information leakage borne by each group, is itself a form of harm, and adopt a compensatory-fairness framework in which a group that involuntarily bears greater privacy exposure is owed proportio

Record details

Published: 18 July 2026
Source: arXiv cs.CR (AI security)
Category: Research
Topics: Bias & fairness · Privacy
Retrieved: 21 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.CY · 21 July 2026

Same publisher byline · Shared topic: Bias & fairness

Fair Finetuning Mitigates Distribution Inference Attacks

arXiv · 1 June 2026

Shared topic: Bias & fairness · Shared topic: Privacy

Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms

arXiv · 16 July 2026

Shared topic: Bias & fairness · Shared topic: Privacy

Trustworthy Privacy-Preserving Multimodal Federated Learning for Personalised Breast Cancer Prediction

arXiv · 21 July 2026

Shared topic: Bias & fairness · Shared topic: Privacy

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification

arXiv cs.CR (AI security) · 23 July 2026

Shared topic: Bias & fairness · Shared topic: Privacy

Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

arXiv fairness query · 8 July 2026

How to cite this record

ethics.ai (18 July 2026), “Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning,” evidence record 12244, https://ethics.ai/record/12244 (originally published by arXiv cs.CR (AI security)).

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.