Toward Individual Fairness Without Centralized Data: Selective Counterfactual Consistency for Vertical Federated Learning

• URL: http://arxiv.org/abs/2605.07117v1
• Date: Fri, 08 May 2026 01:50:06 GMT
• Title: Toward Individual Fairness Without Centralized Data: Selective Counterfactual Consistency for Vertical Federated Learning
• Abstract summary: We propose a server-centric framework for enforcing selective counterfactual consistency ( SCC-VFL) at the individual level in vertical federated learning (VFL)<n> SCC-VFL maintains or improves predictive accuracy while sharply reducing decision flip rates by up to 98% relative to strong baselines.<n>It also lowers attribute-inference attack success and improves robustness, demonstrating favorable utility-fairness-privacy trade-offs in realistic VFL deployments.
• Score: 16.277579974537996
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When algorithmic decisions depend on data distributed across institutions, how can we ensure that an individual's outcome does not change arbitrarily based on a protected attribute? We study this question in vertical federated learning (VFL), where features are split across parties, sensitive attributes may be private, and proxies for protected characteristics can be scattered across institutional boundaries under strict privacy constraints. Our focus is on individual-level counterfactual stability, i.e., per-instance prediction consistency under protected-attribute interventions as formalized in the causal fairness literature, rather than group parity guarantees such as demographic parity or equalized odds. We propose SCC-VFL, a server-centric framework for enforcing selective counterfactual consistency (SCC) at the individual level in VFL. SCC-VFL operationalizes a given policy specification by combining three components: (i) differentially private, graph-free discovery of feature roles into non-descendants, policy-permitted mediators, and impermissible proxies using only a formally private sketch of the sensitive attribute, with a formal per-release privacy that does not extend to the full training pipeline; (ii) masked counterfactual generation that edits only mediators while fixing non-descendants and suppressing proxy leakage; and (iii) server-side enforcement via an SCC consistency loss that penalizes impermissible prediction changes under protected-attribute interventions. Across three real-world datasets spanning credit, healthcare, and criminal justice, SCC-VFL maintains or improves predictive accuracy while sharply reducing decision flip rates by up to 98% relative to strong baselines. It also lowers attribute-inference attack success and improves robustness, demonstrating favorable utility-fairness-privacy trade-offs in realistic VFL deployments.

Related papers

• TADP-RME: A Trust-Adaptive Differential Privacy Framework for Enhancing Reliability of Data-Driven Systems [0.5926203312586108]
  We propose TADP-RME (Trust-Adaptive Differential Privacy with Reverse Manifold Embedding), a framework that enhances reliability under varying levels of user trust.<n>We show improved privacy-utility trade-offs, reducing attack success rates by up to 3.1 percent without significant utility degradation.
  arXiv  Detail & Related papers  (2026-04-09T11:32:57Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy [50.66105844449181]
  Individual Differential Privacy (iDP) promises users control over their privacy, but this promise can be broken in practice.<n>We reveal a previously overlooked vulnerability in sampling-based iDP mechanisms.<n>We propose $(varepsilon_i,_i,overline)$-iDP a privacy contract that uses $$-divergences to provide users with a hard upper bound on their excess vulnerability.
  arXiv  Detail & Related papers  (2026-01-19T10:26:12Z)
• Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation [5.428917824315977]
  Synthetic data generation has emerged as a promising solution to risk-aware data sharing and model development.<n>We propose (Fair Latent Intervention under Privacy guarantees) to address both privacy and fairness concerns in this setting.<n>Unlike the typical setup in fairness-aware data generation, we assume a task-agnostic setup, not reliant on a fixed, defined downstream task, thus offering broader applicability.
  arXiv  Detail & Related papers  (2025-08-29T17:51:42Z)
• Machine Learning with Privacy for Protected Attributes [56.44253915927481]
  We refine the definition of differential privacy (DP) to create a more general and flexible framework that we call feature differential privacy (FDP)<n>Our definition is simulation-based and allows for both addition/removal and replacement variants of privacy, and can handle arbitrary separation of protected and non-protected features.<n>We apply our framework to various machine learning tasks and show that it can significantly improve the utility of DP-trained models when public features are available.
  arXiv  Detail & Related papers  (2025-06-24T17:53:28Z)
• RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility in Autonomous Vehicles [6.3338980105224145]
  Existing FL frameworks struggle to balance privacy, fairness, and robustness, leading to performance disparities across demographic groups.<n>This work explores the trade-off between privacy and fairness in FL-based object detection for AVs and introduces RESFL, an integrated solution optimizing both.<n> RESFL incorporates adversarial privacy disentanglement and uncertainty-guided fairness-aware aggregation.<n>We evaluate RESFL on the FACET dataset and CARLA simulator, assessing accuracy, fairness, privacy resilience, and robustness under varying conditions.
  arXiv  Detail & Related papers  (2025-03-20T15:46:03Z)
• Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI [6.671649946926508]
  We present the first unified large-scale empirical study of privacy-fairness-utility trade-offs in Federated Learning (FL)<n>We compare fairness-awares with Differential Privacy (DP), Homomorphic Encryption (HE), and Secure Multi-Party Encryption (SMC)<n>We uncover unexpected interactions: DP mechanisms can negatively impact fairness, skew, and fairness-awares can inadvertently reduce privacy effectiveness.
  arXiv  Detail & Related papers  (2025-03-20T15:31:01Z)
• Towards Trustworthy Federated Learning [26.25193909843069]
  This paper develops a comprehensive framework to address three critical trustworthy challenges in federated learning (FL)<n>To improve the system's defense against Byzantine attacks, we develop a Two-sided Norm Based Screening mechanism.<n>We also adopt a differential privacy-based scheme to prevent raw data at local clients from being inferred by curious parties.
  arXiv  Detail & Related papers  (2025-03-05T17:25:20Z)
• Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy [55.357715095623554]
  Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. We propose a Bayesian framework, Bayesian Coordinate Differential Privacy (BCDP), that enables feature-specific privacy quantification.
  arXiv  Detail & Related papers  (2024-10-24T03:39:55Z)
• Certifiably Byzantine-Robust Federated Conformal Prediction [49.23374238798428]
  We introduce a novel framework Rob-FCP, which executes robust federated conformal prediction effectively countering malicious clients. We empirically demonstrate the robustness of Rob-FCP against diverse proportions of malicious clients under a variety of Byzantine attacks.
  arXiv  Detail & Related papers  (2024-06-04T04:43:30Z)
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond [57.10914865054868]
  We consider vertical logistic regression (VLR) trained with mini-batch descent gradient. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks.
  arXiv  Detail & Related papers  (2022-07-19T05:47:30Z)
• PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning [12.767527195281042]
  Group fairness in Federated Learning (FL) is challenging because mitigating bias inherently requires using the sensitive attribute values of all clients. We show that this conflict between fairness and privacy in FL can be resolved by combining FL with Secure Multiparty Computation (MPC) and Differential Privacy (DP) In doing so, we propose a method for training group-fair ML models in cross-device FL under complete and formal privacy guarantees.
  arXiv  Detail & Related papers  (2022-05-23T19:26:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.