SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.14607 · 2026

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

Murat Kantarcioglu, Umid Suleymanov, Ilhama Novruzova, Khalid Mammadov, Natavan Hasanova

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
jjgold012/lab-project-fairness — 1 of 12
FunctionStatusWhere it lives
logistic Ran jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("36a1468d01fa52b5")
make_output_dir Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("1156209c2588ddeb")
measure_objective_results Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("29a935537864cec9")
measure_relaxed_results Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("9d5c2c4e42cee3f1")
plot_results Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("74be7e92a19ceaf3")
plot_theta Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("7f96df2d218e1f2a")
show_results Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("c520a2d7f675fe84")
show_summary Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("68d216c70e46d1b5")
show_theta Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("c1ae26fe07192ba6")
solve_convex Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("13e4d76bb3f9c6d2")
solve_one_time_by_type Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("72ed3432d42a637d")
solve_problem_for_fairness Not yet run jjgold012/lab-project-fairness/fairness_project/solver.py
pointer only (licence: NONE) · get_code("3e2205bc7114cf82")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largely examined how privacy-preserving techniques affect fairness, the inverse question-how fairnessenhancing algorithms influence privacy leakage-remains underexplored. We present the first comprehensive study of how fairness interventions affect membership inference privacy risks at the subpopulation level. By adapting the Likelihood Ratio Attack (LiRA) for subgroup auditing, we uncover privacy disparities that aggregate evaluations obscure. We further analyze how Differential Privacy (DP) interacts with fairness-enhancing methods across different categories, showing that DP's privacy benefits and utility costs are unevenly distributed across subpopulations. Our results demonstrate that fairness interventions do not uniformly increase privacy risk; their impact depends on model architecture, subgroup size, and mitigation strategy. These findings reveal that fairness, privacy, and utility must be jointly evaluated at the subpopulation level, and we introduce the first unified empirical framework to support such auditing in practice.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2607.14607")
get_code_for_paper("2607.14607")
have("2607.14607")

Connect an agent — have() is free.