Privacy-Utility Tradeoff

Follow this topic Ask about this topic

This field asks how much sensitive information can be protected without undermining tasks such as medical prediction, recommendation, speech analysis, and agent workflows. Approaches include differential privacy in central, local, and shuffled settings; federated and synthetic data methods; anonymization and representation learning; and selective disclosure that reveals only task-relevant details. Evaluations compare task performance with risks such as membership inference, re-identification, and attribute inference, sometimes also measuring compute costs and fairness. A central tension is that formal protections can substantially reduce utility, while task-specific safeguards may preserve it but depend on realistic threat models and consistent evaluation.

Latest papers

71 papers4 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models
Oct 16, 2026Yiqu Yang, Qiaoyuan Zheng, Yang Tian +2Privacy-Utility Tradeoff Privacy Leakage in Language Models
ETH Zurich · The University of Hong Kong
SHIP: Structured and Hierarchical Insight with Privacy
Oct 15, 2026Kai Chen, Guisi Ni, Albert Cheu +4Differentially Private Synthetic Data Generation Privacy-Utility Tradeoff
University of Virginia · Google Research
PrivCert: Certifying Statement Support under Differential Privacy
Sep 30, 2026Tsubasa Takahashi, Takumi HiraokaDifferential Privacy Privacy-Utility Tradeoff
Acompany Co., Ltd.
Privacy-Friendly Cohort Determination: Sealed, CSP-Independent In-Browser ML Inference of Professional Segments for Identity-Less Advertising
Sep 28, 2026Om Shankar Tiwari, Navnit Shukla, Guanyu Wang +1Online Advertising Privacy-Preserving ML
Applied AI Technical Lead, Google · Principal AI Architect, Snowflake Inc. · Staff Software Engineer, TikTok +1
Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology
Sep 10, 2026Noman Sadiq, Mohsen TooraniElectroencephalography Privacy-Preserving ML
Department of Science and Industry Systems University of South-Eastern Norway Kongsberg, Norway
On the Impact of Anonymization on the Performance of Large Language Models
Sep 10, 2026Tobias Deußer, Max Hahnbück, Lorenz Sparrenberg +3LLM Evaluation Privacy-Preserving Language Models
University of Bonn, Bonn, Germany · 2Fraunhofer IAIS, Sankt Augustin, Germany · 3Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany +1
Demystifying the Privacy-Utility Trade-off in LLM Interactions
Sep 10, 2026Zhenhua Liu, Zhanxu Xie, Junjie Yu +3Privacy-Preserving Language Models Privacy Leakage in Language Models
Soochow University · Beihang University · Suzhou City University +2
Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR
Sep 4, 2026Cory Ilo, Brendan-David John, Doug A. BowmanPrivacy-Utility Tradeoff Privacy-Preserving ML
Virginia Tech Blacksburg, Virginia, USA
DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts
Aug 31, 2026Ibrahim Baroud, Stephen Meisenbacher, Sebastian Möller +2Differential Privacy Privacy-Utility Tradeoff
Quality & Usability Lab, Technical University of Berlin, Berlin, Germany · German Research Center for Artificial Intelligence (DFKI), Berlin, Germany · Technical University of Munich, School of CIT, Garching, Germany +1
Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization
Aug 31, 2026Dishu Yang, Jingjing Liu, Jize LiLLM Alignment Memorization in Language Models
Khoury College of Computer Sciences Northeastern University San Jose, USA · Department of Electrical Engineering and Computer Sciences University of California, Berkeley Berkeley, USA · Department of Economics Boston University Boston, USA
Performative Privacy: When Differential Privacy Maximizes Utility
Aug 28, 2026Uddalak Mukherjee, Edwige Cyffers, Yann ChevaleyreData Leakage Differential Privacy
Dauphine PSL · CNRS Dauphine PSL
Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations
Aug 27, 2026Leon Ranke, Wolfgang Hübner, Ronny Hug +2Privacy-Preserving ML Privacy-Utility Tradeoff
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB), Gutleuthausstraße 1, 76275 Ettlingen, Germany · Karlsruhe Institute of Technology (KIT)
Defending Wearable VLMs Against Private Attribute Inference
Aug 26, 2026Zhimin Li, Pan Wang, Jingxian Chen +4Privacy Protection in VLMs Privacy-Utility Tradeoff
Swanson School of Engineering, University of Pittsburgh · North Allegheny Senior High · College of Engineering, Michigan State University +1
Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy
Aug 19, 2026Stephen Meisenbacher, Vlad Garbuz, Chirill Donos +5Hate Speech Detection Privacy-Utility Tradeoff
Technical University of Munich, Chair of Human-Centered Computing, Munich, Germany · Munich Center for Machine Learning, Munich, Germany · Munich Data Science Institute, Munich, Germany +3
Information Bottleneck under Perfect Privacy
Aug 11, 2026Junle Zhong, Mohamad Assaad, Sreejith SreekumarInformation Bottleneck Privacy-Preserving ML
Laboratoire des Signaux et Syst`emes (L2S), CNRS, CentraleSup´elec, Universit´e Paris-Saclay, 91190 Gif-sur-Yvette, France
Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs
Aug 5, 2026Sareer Ul Amin, Muhammad Ayaz, Muhammad Munsif +1Privacy-Preserving ML Privacy-Utility Tradeoff
Ulsan National Institute of Science and Technology (UNIST), Ulsan 44919, Republic of Korea · College of Art and Technology, Chung-Ang University, Anseong, 17546, South Korea
Shapley-Value-Based Feature Attribution for Data Masking
Jul 31, 2026Xinxue, Qu, Francis Bilson Darku +1Shapley Value Attribution Privacy-Utility Tradeoff
Shawn · Department of Information Technology, Analytics, and Operations, Mendoza College of Business University of Notre Dame, South Bend, IN, U.S.A. · Department of Information Systems, W. P. Carey School of Business Arizona State University, Tempe, AZ, U.S.A.
Privacy Preserving Recommender Systems Balancing Personalization with Privacy
Jul 14, 2026Ranjeet K Jha, Venkata Suresh GummadilliDifferential Privacy Recommender Systems
College of Natural Sciences, The University of Texas at Austin, Austin, TX 78712 USA
Privacy-Aware Collaborative and Distributed Bayesian Optimization
Jul 13, 2026Aditya Rane, Sathwik Yamana, Paritosh Ramanan +2Bayesian Optimization Privacy-Utility Tradeoff
School of Industrial Engineering and Management Oklahoma State University, Stillwater, OK, USA
Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data
Jul 8, 2026Vinícius Gabriel Angelozzi, Héber H. ArcoleziAlgorithmic Fairness Group Fairness
Centre Inria de l’Université Grenoble Alpes · ÉTS Montréal, Inria Grenoble
REAN: Reconstruction-aware ECG Anonymization Based on Privacy--Utility Orthogonality
Jul 7, 2026Taerin Ki, Sunghwan Park, Junyoung Park +1Biometric Identification Electrocardiography
Chung-Ang University Seoul, South Korea
PromptPET: Privacy-Utility Optimized Prompt Obfuscation
Jul 3, 2026Ke Yang, Olivia Figueira, Umar Iqbal +1Privacy-Preserving Language Models Privacy-Utility Tradeoff
University of California, Irvine Irvine, CA, USA · Washington University in St. Louis St. Louis, MO, USA
SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure
Jul 2, 2026Dylan Zongmin LiuAutomated Negotiation AI Agent Benchmarks
Stanford University
Predictability as a Fine-Grained Measure for Privacy
Jun 18, 2026Linda Lu, Karthik SridharanDifferential Privacy Privacy-Utility Tradeoff
Cornell University
TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction
Jun 17, 2026Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun +2Privacy-Preserving Language Models Privacy Leakage in Language Models
Dept. of Electrical Engineering, POSTECH · Grad. School of Artificial Intelligence, POSTECH · Grad. School of Metaverse, KAIST +1
PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization
Jun 16, 2026Arshia Ilaty, Hossein Shirazi, Manasi Chitale +5Synthetic Tabular Data Generation Tabular Data Synthesis
San Diego State University, San Diego, CA 92182 USA. · University of California, Irvine, CA 92697 USA.
CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents
Jun 10, 2026Siyu Shen, Fenghao Xu, Wenrui Diao +1Mobile GUI Automation Privacy-Utility Tradeoff
The Chinese University of Hong Kong · Southeast University · Shandong University
InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization
Jun 4, 2026Xueyang Wu, Siyuan Liu, Kezhuo Yang +1Audio Representation Learning Depression Detection
Shenzhen NeurStar Inc., China · University of York, United Kingdom · Shanghai Jiao Tong University, China
Privacy-Robust Incrementality Measurement for Advertising Systems under Signal Loss
Jun 2, 2026Prashant Shekhar, Caroline HowardOnline Advertising Partial Identification
Department of Mathematics Embry-Riddle Aeronautical University Daytona Beach, FL, USA
The Impact of Temporal Granularity on Socio-Demographic Inference from Household Load Profiles
Jun 2, 2026Dejan Radovanovic, Maximilian Schirl, Andreas Unterweger +1Time Series Classification User Attribute Inference Attacks
Center for Secure Energy Informatics, Salzburg University of Applied Sciences, Puch bei Hallein, Austria · Paris Lodron University of Salzburg, Salzburg, Austria

Oct 16, 2026J/K move · Enter open · S save

TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models

Yiqu Yang, Qiaoyuan Zheng, Yang Tian, Yu Fan+1

ETH Zurich · The University of Hong Kong

Privacy-Utility Tradeoff Privacy Leakage in Language Models Privacy-Preserving ML Privacy Auditing

Open paper AskPDF arXiv

Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confidence score. These fields support downstream decisions but may reveal information beyond a recipient's authorization. We introduce TUPLE-Bench (Typed decision models' Utility and Privacy Leakage Evaluation Benchmark), a benchmark of paired synthetic cases in which recipients may learn a coarse operational category but not its fine-grained cause. Across nine models, instructions to withhold the cause fail to protect it: 91.88%-99.93% of responses reveal the cause through direct selection or residual scores. Even when causes are excluded from the candidate set, full outputs enable 62.85%-75.35% recovery on held-out cases, compared with 51.04%-57.64% using only the selected category (50% chance). Full outputs also reduce mean downstream cost in all 27 model-task comparisons. However, confidence fields increase leakage without consistently reducing cost. We further introduce workflow-constrained privacy quantization (WCPQ), which reduces secret recovery while preserving the behavior and cost of specified downstream workflows. Our findings highlight the need to audit decision interfaces field by field and workflow by workflow.