An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy

• URL: http://arxiv.org/abs/2509.04290v1
• Date: Thu, 04 Sep 2025 15:02:10 GMT
• Title: An Interactive Framework for Finding the Optimal Trade-off in Differential Privacy
• Authors: Yaohong Yang, Aki Rehn, Sammie Katt, Antti Honkela, Samuel Kaski,
• Abstract summary: We introduce Differential privacy (DP) as the standard for privacy-preserving analysis, and introduce a fundamental trade-off between privacy guarantees and model performance.<n>In particular, we present the user with hypothetical trade-off curves and ask them to pick their preferred trade-off.<n>Our experiments on differentially private logistic regression and deep transfer learning across six real-world datasets show that our method converges to the optimal privacy-accuracy trade-off.
• Score: 20.038766371144526
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differential privacy (DP) is the standard for privacy-preserving analysis, and introduces a fundamental trade-off between privacy guarantees and model performance. Selecting the optimal balance is a critical challenge that can be framed as a multi-objective optimization (MOO) problem where one first discovers the set of optimal trade-offs (the Pareto front) and then learns a decision-maker's preference over them. While a rich body of work on interactive MOO exists, the standard approach -- modeling the objective functions with generic surrogates and learning preferences from simple pairwise feedback -- is inefficient for DP because it fails to leverage the problem's unique structure: a point on the Pareto front can be generated directly by maximizing accuracy for a fixed privacy level. Motivated by this property, we first derive the shape of the trade-off theoretically, which allows us to model the Pareto front directly and efficiently. To address inefficiency in preference learning, we replace pairwise comparisons with a more informative interaction. In particular, we present the user with hypothetical trade-off curves and ask them to pick their preferred trade-off. Our experiments on differentially private logistic regression and deep transfer learning across six real-world datasets show that our method converges to the optimal privacy-accuracy trade-off with significantly less computational cost and user interaction than baselines.

Related papers

• Tackling Privacy Heterogeneity in Differentially Private Federated Learning [33.2985262258717]
  We present the first systematic study of privacy-aware client selection in Differentially private federated learning (DP-FL)<n>We propose a privacy-aware client selection strategy, formulated as a convex optimization problem, that adaptively adjusts selection probabilities to minimize training error.<n>Our approach achieves up to a 10% improvement in test accuracy on benchmark datasets.
  arXiv  Detail & Related papers  (2026-02-26T05:20:37Z)
• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It [81.50711040539566]
  Current large language model (LLM) development treats task-solving and preference alignment as separate challenges.<n>We introduce PREFDISCO, an evaluation methodology that transforms static benchmarks into interactive personalization tasks.<n>Our framework creates scenarios where identical questions require different reasoning chains depending on user context.
  arXiv  Detail & Related papers  (2025-09-30T18:55:28Z)
• Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks [81.44256822500257]
  RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences.<n> RLHF exhibits insufficient compliance capabilities when confronted with complex multi-instruction tasks.<n>We propose a novel Multi-level Aware Preference Learning (MAPL) framework, capable of enhancing multi-instruction capabilities.
  arXiv  Detail & Related papers  (2025-05-19T08:33:11Z)
• Improved Algorithms for Differentially Private Language Model Alignment [12.611907955831597]
  We propose novel algorithms for privacy-preserving alignment.<n>Our framework can be deployed on two celebrated alignment techniques.<n>One of our algorithms, DP-AdamW, combined with DPO, surpasses existing methods, improving alignment quality by up to 15% under moderate privacy budgets.
  arXiv  Detail & Related papers  (2025-05-13T16:18:59Z)
• Multi-Objective Optimization for Privacy-Utility Balance in Differentially Private Federated Learning [12.278668095136098]
  Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data.<n>We propose an adaptive clipping mechanism that dynamically adjusts the clipping norm using a multi-objective optimization framework.<n>Our results show that adaptive clipping consistently outperforms fixed-clipping baselines, achieving improved accuracy under the same privacy constraints.
  arXiv  Detail & Related papers  (2025-03-27T04:57:05Z)
• Personalized Language Models via Privacy-Preserving Evolutionary Model Merging [53.97323896430374]
  Personalization in language models aims to tailor model behavior to individual users or user groups.<n>We propose Privacy-Preserving Model Merging via Evolutionary Algorithms (PriME)<n>PriME employs gradient-free methods to directly optimize utility while reducing privacy risks.<n>Experiments on the LaMP benchmark show that PriME consistently outperforms a range of baselines, achieving up to a 45% improvement in task performance.
  arXiv  Detail & Related papers  (2025-03-23T09:46:07Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning [23.563789510998333]
  Federated learning (FL) enables multiple clients to collaboratively learn a shared model without sharing their individual data. Differential privacy has emerged as a prevalent technique in FL, safeguarding the privacy of individual user data while impacting utility and training efficiency. This paper systematically formulates an efficiency-constrained utility-privacy bi-objective optimization problem in DPFL.
  arXiv  Detail & Related papers  (2023-12-27T12:37:55Z)
• Theoretically Principled Federated Learning for Balancing Privacy and Utility [61.03993520243198]
  We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters. It can achieve personalized utility-privacy trade-off for each model parameter, on each client, at each communication round in federated learning.
  arXiv  Detail & Related papers  (2023-05-24T13:44:02Z)
• Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility [28.946180502706504]
  We argue that machine learning pipelines should not favor one objective over another. We propose impartially-specified models that show the inherent trade-offs between the objectives. We provide an answer to the question of where fairness mitigation should be integrated within a privacy-aware ML pipeline.
  arXiv  Detail & Related papers  (2023-02-17T23:23:45Z)

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.