Differential Privacy Papers
LightNews LightNews
dppapers.bsky.social
Differential Privacy Papers
@dppapers.bsky.social
470 followers 0 following 890 posts
🤖 new arXiv preprints mentioning "differential privacy" or "differentially private" in the title/abstract/metadata - unrelated quantum/FL papers + updates from https://differentialprivacy.org [Under construction.]
differentialprivacy.org
Posts Media Videos Starter Packs
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 8h
On the Sample Complexity of Differentially Private Policy Optimization

Yi He, Xingyu Zhou

http://arxiv.org/abs/2510.21060
On the Sample Complexity of Differentially Private Policy Optimization Yi He, Xingyu Zhou http://arxiv.org/abs/2510.21060 Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and large language model training. The increasing deployment of PO in sensitive domains, however, raises significant privacy concerns. In this paper, we initiate a theoretical study of differentially private policy optimization, focusing explicitly on its sample complexity. We first formalize an appropriate definition of differential privacy (DP) tailored to PO, addressing the inherent challenges arising from on-policy learning dynamics and the subtlety involved in defining the unit of privacy. We then systematically analyze the sample complexity of widely-used PO algorithms, including policy gradient (PG), natural policy gradient (NPG) and more, under DP constraints and various settings, via a unified framework. Our theoretical results demonstrate that privacy costs can often manifest as lower-order terms in the sample complexity, while also highlighting subtle yet important observations in private PO settings. These offer valuable practical insights for privacy-preserving PO algorithms.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 8h
Privacy Guarantee for Nash Equilibrium Computation of Aggregative Games Based on Pointwise Maximal Leakage

Zhaoyang Cheng, Guanpu Chen, Tobias J. Oechtering, Mikael Skoglund

http://arxiv.org/abs/2510.21668
Privacy Guarantee for Nash Equilibrium Computation of Aggregative Games Based on Pointwise Maximal Leakage Zhaoyang Cheng, Guanpu Chen, Tobias J. Oechtering, Mikael Skoglund http://arxiv.org/abs/2510.21668 Privacy preservation has served as a key metric in designing Nash equilibrium (NE) computation algorithms. Although differential privacy (DP) has been widely employed for privacy guarantees, it does not exploit prior distributional knowledge of datasets and is ineffective in assessing information leakage for correlated datasets. To address these concerns, we establish a pointwise maximal leakage (PML) framework when computing NE in aggregative games. By incorporating prior knowledge of players' cost function datasets, we obtain a precise and computable upper bound of privacy leakage with PML guarantees. In the entire view, we show PML refines DP by offering a tighter privacy guarantee, enabling flexibility in designing NE computation. Also, in the individual view, we reveal that the lower bound of PML can exceed the upper bound of DP by constructing specific correlated datasets. The results emphasize that PML is a more proper privacy measure than DP since the latter fails to adequately capture privacy leakage in correlated datasets. Moreover, we conduct experiments with adversaries who attempt to infer players' private information to illustrate the effectiveness of our framework.
1
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 8h
Toward provably private analytics and insights into GenAI use

Albert Cheu, Artem Lagzdin, Brett McLarnon, Daniel Ramage, Katharine Daly, Marco Gruteser, Peter Kairouz, Rakshita Tandon, Stanislav Chiknavaryan, Timon Van Overveldt, Zoe Gong

http://arxiv.org/abs/2510.21684
Toward provably private analytics and insights into GenAI use Albert Cheu, Artem Lagzdin, Brett McLarnon, Daniel Ramage, Katharine Daly, Marco Gruteser, Peter Kairouz, Rakshita Tandon, Stanislav Chiknavaryan, Timon Van Overveldt, Zoe Gong http://arxiv.org/abs/2510.21684 Large-scale systems that compute analytics over a fleet of devices must achieve high privacy and security standards while also meeting data quality, usability, and resource efficiency expectations. We present a next-generation federated analytics system that uses Trusted Execution Environments (TEEs) based on technologies like AMD SEV-SNP and Intel TDX to provide verifiable privacy guarantees for all server-side processing. In our system, devices encrypt and upload data, tagging it with a limited set of allowable server-side processing steps. An open source, TEE-hosted key management service guarantees that the data is accessible only to those steps, which are themselves protected by TEE confidentiality and integrity assurance guarantees. The system is designed for flexible workloads, including processing unstructured data with LLMs (for structured summarization) before aggregation into differentially private insights (with automatic parameter tuning). The transparency properties of our system allow any external party to verify that all raw and derived data is processed in TEEs, protecting it from inspection by the system operator, and that differential privacy is applied to all released results. This system has been successfully deployed in production, providing helpful insights into real-world GenAI experiences.
2
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 3d
Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy

Xiang Li, Buxin Su, Chendi Wang, Qi Long, Weijie J. Su

http://arxiv.org/abs/2510.19934
Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via $f$-Differential Privacy Xiang Li, Buxin Su, Chendi Wang, Qi Long, Weijie J. Su http://arxiv.org/abs/2510.19934 Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifying the privacy budget of private FL algorithms is challenging due to the co-existence of complex algorithmic components such as decentralized communication and local updates. This paper addresses privacy accounting for two decentralized FL algorithms within the $f$-differential privacy ($f$-DP) framework. We develop two new $f$-DP-based accounting methods tailored to decentralized settings: Pairwise Network $f$-DP (PN-$f$-DP), which quantifies privacy leakage between user pairs under random-walk communication, and Secret-based $f$-Local DP (Sec-$f$-LDP), which supports structured noise injection via shared secrets. By combining tools from $f$-DP theory and Markov chain concentration, our accounting framework captures privacy amplification arising from sparse communication, local iterations, and correlated noise. Experiments on synthetic and real datasets demonstrate that our methods yield consistently tighter $(\epsilon,\delta)$ bounds and improved utility compared to R\'enyi DP-based approaches, illustrating the benefits of $f$-DP in decentralized privacy accounting.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 3d
ADP-VRSGP: Decentralized Learning with Adaptive Differential Privacy via Variance-Reduced Stochastic Gradient Push

Xiaoming Wu, Teng Liu, Xin Wang, Ming Yang, Jiguo Yu

http://arxiv.org/abs/2510.20157
ADP-VRSGP: Decentralized Learning with Adaptive Differential Privacy via Variance-Reduced Stochastic Gradient Push Xiaoming Wu, Teng Liu, Xin Wang, Ming Yang, Jiguo Yu http://arxiv.org/abs/2510.20157 Differential privacy is widely employed in decentralized learning to safeguard sensitive data by introducing noise into model updates. However, existing approaches that use fixed-variance noise often degrade model performance and reduce training efficiency. To address these limitations, we propose a novel approach called decentralized learning with adaptive differential privacy via variance-reduced stochastic gradient push (ADP-VRSGP). This method dynamically adjusts both the noise variance and the learning rate using a stepwise-decaying schedule, which accelerates training and enhances final model performance while providing node-level personalized privacy guarantees. To counteract the slowed convergence caused by large-variance noise in early iterations, we introduce a progressive gradient fusion strategy that leverages historical gradients. Furthermore, ADP-VRSGP incorporates decentralized push-sum and aggregation techniques, making it particularly suitable for time-varying communication topologies. Through rigorous theoretical analysis, we demonstrate that ADP-VRSGP achieves robust convergence with an appropriate learning rate, significantly improving training stability and speed. Experimental results validate that our method outperforms existing baselines across multiple scenarios, highlighting its efficacy in addressing the challenges of privacy-preserving decentralized learning.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 3d
Adversary-Aware Private Inference over Wireless Channels

Mohamed Seif, Malcolm Egan, Andrea J. Goldsmith, H. Vincent Poor

http://arxiv.org/abs/2510.20518
Adversary-Aware Private Inference over Wireless Channels Mohamed Seif, Malcolm Egan, Andrea J. Goldsmith, H. Vincent Poor http://arxiv.org/abs/2510.20518 AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and perception tasks such as in autonomous driving and environmental monitoring. AI systems rely both on efficient model learning and inference. In the inference phase, features extracted from sensing data are utilized for prediction tasks (e.g., classification or regression). In edge networks, sensors and model servers are often not co-located, which requires communication of features. As sensitive personal data can be reconstructed by an adversary, transformation of the features are required to reduce the risk of privacy violations. While differential privacy mechanisms provide a means of protecting finite datasets, protection of individual features has not been addressed. In this paper, we propose a novel framework for privacy-preserving AI-based sensing, where devices apply transformations of extracted features before transmission to a model server.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 3d
On Optimal Hyperparameters for Differentially Private Deep Transfer Learning

Aki Rehn, Linzh Zhao, Mikko A. Heikkilä, Antti Honkela

http://arxiv.org/abs/2510.20616
On Optimal Hyperparameters for Differentially Private Deep Transfer Learning Aki Rehn, Linzh Zhao, Mikko A. Heikkilä, Antti Honkela http://arxiv.org/abs/2510.20616 Differentially private (DP) transfer learning, i.e., fine-tuning a pretrained model on private data, is the current state-of-the-art approach for training large models under privacy constraints. We focus on two key hyperparameters in this setting: the clipping bound $C$ and batch size $B$. We show a clear mismatch between the current theoretical understanding of how to choose an optimal $C$ (stronger privacy requires smaller $C$) and empirical outcomes (larger $C$ performs better under strong privacy), caused by changes in the gradient distributions. Assuming a limited compute budget (fixed epochs), we demonstrate that the existing heuristics for tuning $B$ do not work, while cumulative DP noise better explains whether smaller or larger batches perform better. We also highlight how the common practice of using a single $(C,B)$ setting across tasks can lead to suboptimal performance. We find that performance drops especially when moving between loose and tight privacy and between plentiful and limited compute, which we explain by analyzing clipping as a form of gradient re-weighting and examining cumulative DP noise.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 4d
ConvXformer: Differentially Private Hybrid ConvNeXt-Transformer for Inertial Navigation

Omer Tariq, Muhammad Bilal, Muneeb Ul Hassan, Dongsoo Han, Jon Crowcroft

http://arxiv.org/abs/2510.19352
ConvXformer: Differentially Private Hybrid ConvNeXt-Transformer for Inertial Navigation Omer Tariq, Muhammad Bilal, Muneeb Ul Hassan, Dongsoo Han, Jon Crowcroft http://arxiv.org/abs/2510.19352 Data-driven inertial sequence learning has revolutionized navigation in GPS-denied environments, offering superior odometric resolution compared to traditional Bayesian methods. However, deep learning-based inertial tracking systems remain vulnerable to privacy breaches that can expose sensitive training data. \hl{Existing differential privacy solutions often compromise model performance by introducing excessive noise, particularly in high-frequency inertial measurements.} In this article, we propose ConvXformer, a hybrid architecture that fuses ConvNeXt blocks with Transformer encoders in a hierarchical structure for robust inertial navigation. We propose an efficient differential privacy mechanism incorporating adaptive gradient clipping and gradient-aligned noise injection (GANI) to protect sensitive information while ensuring model performance. Our framework leverages truncated singular value decomposition for gradient processing, enabling precise control over the privacy-utility trade-off. Comprehensive performance evaluations on benchmark datasets (OxIOD, RIDI, RoNIN) demonstrate that ConvXformer surpasses state-of-the-art methods, achieving more than 40% improvement in positioning accuracy while ensuring $(\epsilon,\delta)$-differential privacy guarantees. To validate real-world performance, we introduce the Mech-IO dataset, collected from the mechanical engineering building at KAIST, where intense magnetic fields from industrial equipment induce significant sensor perturbations. This demonstrated robustness under severe environmental distortions makes our framework well-suited for secure and intelligent navigation in cyber-physical systems.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 4d
Differentially Private E-Values

Daniel Csillag, Diego Mesquita

http://arxiv.org/abs/2510.18654
Differentially Private E-Values Daniel Csillag, Diego Mesquita http://arxiv.org/abs/2510.18654 E-values have gained prominence as flexible tools for statistical inference and risk control, enabling anytime- and post-hoc-valid procedures under minimal assumptions. However, many real-world applications fundamentally rely on sensitive data, which can be leaked through e-values. To ensure their safe release, we propose a general framework to transform non-private e-values into differentially private ones. Towards this end, we develop a novel biased multiplicative noise mechanism that ensures our e-values remain statistically valid. We show that our differentially private e-values attain strong statistical power, and are asymptotically as powerful as their non-private counterparts. Experiments across online risk monitoring, private healthcare, and conformal e-prediction demonstrate our approach's effectiveness and illustrate its broad applicability.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 5d
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control

Yuzheng Hu, Ryan McKenna, Da Yu, Shanshan Wu, Han Zhao, Zheng Xu, Peter Kairouz

http://arxiv.org/abs/2510.18232
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control Yuzheng Hu, Ryan McKenna, Da Yu, Shanshan Wu, Han Zhao, Zheng Xu, Peter Kairouz http://arxiv.org/abs/2510.18232 Generating high-quality synthetic text under differential privacy (DP) is critical for training and evaluating language models without compromising user privacy. Prior work on synthesizing DP datasets often fail to preserve key statistical attributes, suffer utility loss from the noise required by DP, and lack fine-grained control over generation. To address these challenges, we make two contributions. First, we introduce a hierarchical framework that decomposes DP synthetic text generation into two subtasks: feature learning and conditional text generation. This design explicitly incorporates learned features into the generation process and simplifies the end-to-end synthesis task. Through systematic ablations, we identify the most effective configuration: a rich tabular schema as feature, a DP tabular synthesizer, and a DP fine-tuned conditional generator, which we term ACTG (Attribute-Conditioned Text Generation). Second, we propose Anchored RL (ARL), a post-training method that improves the instruction-following ability of ACTG for conditional generation. ARL combines RL to boost control with an SFT anchor on best-of-$N$ data to prevent reward hacking. Together, these components form our end-to-end algorithm ACTG-ARL, which advances both the quality of DP synthetic text (+20% MAUVE over prior work) and the control of the conditional generator under strong privacy guarantees.
1
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 5d
Uniformity Testing under User-Level Local Privacy

Clément L. Canonne, Abigail Gentle, Vikrant Singhal

http://arxiv.org/abs/2510.18379
Uniformity Testing under User-Level Local Privacy Clément L. Canonne, Abigail Gentle, Vikrant Singhal http://arxiv.org/abs/2510.18379 We initiate the study of distribution testing under \emph{user-level} local differential privacy, where each of $n$ users contributes $m$ samples from the unknown underlying distribution. This setting, albeit very natural, is significantly more challenging that the usual locally private setting, as for the same parameter $\varepsilon$ the privacy guarantee must now apply to a full batch of $m$ data points. While some recent work consider distribution \emph{learning} in this user-level setting, nothing was known for even the most fundamental testing task, uniformity testing (and its generalization, identity testing). We address this gap, by providing (nearly) sample-optimal user-level LDP algorithms for uniformity and identity testing. Motivated by practical considerations, our main focus is on the private-coin, symmetric setting, which does not require users to share a common random seed nor to have been assigned a globally unique identifier.
1
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 5d
Exploring Membership Inference Vulnerabilities in Clinical Large Language Models

Alexander Nemecek, Zebin Yun, Zahra Rahmani, Yaniv Harel, Vipin Chaudhary, Mahmood Sharif, Erman Ayday

http://arxiv.org/abs/2510.18674
Exploring Membership Inference Vulnerabilities in Clinical Large Language Models Alexander Nemecek, Zebin Yun, Zahra Rahmani, Yaniv Harel, Vipin Chaudhary, Mahmood Sharif, Erman Ayday http://arxiv.org/abs/2510.18674 As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the healthcare sector. Fine-tuning LLMs on sensitive electronic health record (EHR) data improves domain alignment but also raises the risk of exposing patient information through model behaviors. In this work-in-progress, we present an exploratory empirical study on membership inference vulnerabilities in clinical LLMs, focusing on whether adversaries can infer if specific patient records were used during model training. Using a state-of-the-art clinical question-answering model, Llemr, we evaluate both canonical loss-based attacks and a domain-motivated paraphrasing-based perturbation strategy that more realistically reflects clinical adversarial conditions. Our preliminary findings reveal limited but measurable membership leakage, suggesting that current clinical LLMs provide partial resistance yet remain susceptible to subtle privacy risks that could undermine trust in clinical AI adoption. These results motivate continued development of context-aware, domain-specific privacy evaluations and defenses such as differential privacy fine-tuning and paraphrase-aware training, to strengthen the security and trustworthiness of healthcare AI systems.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
High-Dimensional Privacy-Utility Dynamics of Noisy Stochastic Gradient Descent on Least Squares

Shurong Lin, Eric D. Kolaczyk, Adam Smith, Elliot Paquette

http://arxiv.org/abs/2510.16687
High-Dimensional Privacy-Utility Dynamics of Noisy Stochastic Gradient Descent on Least Squares Shurong Lin, Eric D. Kolaczyk, Adam Smith, Elliot Paquette http://arxiv.org/abs/2510.16687 The interplay between optimization and privacy has become a central theme in privacy-preserving machine learning. Noisy stochastic gradient descent (SGD) has emerged as a cornerstone algorithm, particularly in large-scale settings. These variants of gradient methods inject carefully calibrated noise into each update to achieve differential privacy, the gold standard notion of rigorous privacy guarantees. Prior work primarily provides various bounds on statistical risk and privacy loss for noisy SGD, yet the \textit{exact} behavior of the process remains unclear, particularly in high-dimensional settings. This work leverages a diffusion approach to analyze noisy SGD precisely, providing a continuous-time perspective that captures both statistical risk evolution and privacy loss dynamics in high dimensions. Moreover, we study a variant of noisy SGD that does not require explicit knowledge of gradient sensitivity, unlike existing work that assumes or enforces sensitivity through gradient clipping. Specifically, we focus on the least squares problem with $\ell_2$ regularization.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
Efficient derandomization of differentially private counting queries

Surendra Ghentiyala

http://arxiv.org/abs/2510.16959
Efficient derandomization of differentially private counting queries Surendra Ghentiyala http://arxiv.org/abs/2510.16959 Differential privacy for the 2020 census required an estimated 90 terabytes of randomness [GL20], an amount which may be prohibitively expensive or entirely infeasible to generate. Motivated by these practical concerns, [CSV25] initiated the study of the randomness complexity of differential privacy, and in particular, the randomness complexity of $d$ counting queries. This is the task of outputting the number of entries in a dataset that satisfy predicates $\mathcal{P}_1, \dots, \mathcal{P}_d$ respectively. They showed the rather surprising fact that though any reasonably accurate, $\varepsilon$-differentially private mechanism for one counting query requires $1-O(\varepsilon)$ bits of randomness in expectation, there exists a fairly accurate mechanism for $d$ counting queries which requires only $O(\log d)$ bits of randomness in expectation. The mechanism of [CSV25] is inefficient (not polynomial time) and relies on a combinatorial object known as rounding schemes. Here, we give a polynomial time mechanism which achieves nearly the same randomness complexity versus accuracy tradeoff as that of [CSV25]. Our construction is based on the following simple observation: after a randomized shift of the answer to each counting query, the answer to many counting queries remains the same regardless of whether we add noise to that coordinate or not. This allows us to forgo the step of adding noise to the result of many counting queries. Our mechanism does not make use of rounding schemes. Therefore, it provides a different -- and, in our opinion, clearer -- insight into the origins of the randomness savings that can be obtained by batching $d$ counting queries. Therefore, it provides a different -- and, in our opinion, clearer -- insight into the origins of the randomness savings that can be obtained by batching $d$ counting queries.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees

Shurong Lin, Aleksandra Slavković, Deekshith Reddy Bhoomireddy

http://arxiv.org/abs/2510.16974
Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees Shurong Lin, Aleksandra Slavković, Deekshith Reddy Bhoomireddy http://arxiv.org/abs/2510.16974 In social sciences, small- to medium-scale datasets are common and linear regression (LR) is canonical. In privacy-aware settings, much work has focused on differentially private (DP) LR, but mostly on point estimation with limited attention to uncertainty quantification. Meanwhile, synthetic data generation (SDG) is increasingly important for reproducibility studies, yet current DP LR methods do not readily support it. Mainstream SDG approaches are either tailored to discretized data, making them less suitable for continuous regression, or rely on deep models that require large datasets, limiting their use for the smaller, continuous data typical in social science. We propose a method for LR with valid inference under Gaussian DP: a DP bias-corrected estimator with asymptotic confidence intervals (CIs) and a general SDG procedure in which regression on the synthetic data matches our DP regression. Our binning-aggregation strategy is effective in small- to moderate-dimensional settings. Experiments show our method (1) improves accuracy over existing methods, (2) provides valid CIs, and (3) produces more reliable synthetic data for downstream ML tasks than current DP SDGs.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
ALPINE: A Lightweight and Adaptive Privacy-Decision Agent Framework for Dynamic Edge Crowdsensing

Guanjie Cheng, Siyang Liu, Junqin Huang, Xinkui Zhao, Yin Wang, Mengying Zhu, Linghe Kong, Shuiguang Deng

http://arxiv.org/abs/2510.17162
ALPINE: A Lightweight and Adaptive Privacy-Decision Agent Framework for Dynamic Edge Crowdsensing Guanjie Cheng, Siyang Liu, Junqin Huang, Xinkui Zhao, Yin Wang, Mengying Zhu, Linghe Kong, Shuiguang Deng http://arxiv.org/abs/2510.17162 Mobile edge crowdsensing (MECS) systems continuously generate and transmit user data in dynamic, resource-constrained environments, exposing users to significant privacy threats. In practice, many privacy-preserving mechanisms build on differential privacy (DP). However, static DP mechanisms often fail to adapt to evolving risks, for example, shifts in adversarial capabilities, resource constraints and task requirements, resulting in either excessive noise or inadequate protection. To address this challenge, we propose ALPINE, a lightweight, adaptive framework that empowers terminal devices to autonomously adjust differential privacy levels in real time. ALPINE operates as a closed-loop control system consisting of four modules: dynamic risk perception, privacy decision via twin delayed deep deterministic policy gradient (TD3), local privacy execution and performance verification from edge nodes. Based on environmental risk assessments, we design a reward function that balances privacy gains, data utility and energy cost, guiding the TD3 agent to adaptively tune noise magnitude across diverse risk scenarios and achieve a dynamic equilibrium among privacy, utility and cost. Both the collaborative risk model and pretrained TD3-based agent are designed for low-overhead deployment. Extensive theoretical analysis and real-world simulations demonstrate that ALPINE effectively mitigates inference attacks while preserving utility and cost, making it practical for large-scale edge applications.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
Optimal Best Arm Identification under Differential Privacy

Marc Jourdan, Achraf Azize

http://arxiv.org/abs/2510.17348
Optimal Best Arm Identification under Differential Privacy Marc Jourdan, Achraf Azize http://arxiv.org/abs/2510.17348 Best Arm Identification (BAI) algorithms are deployed in data-sensitive applications, such as adaptive clinical trials or user studies. Driven by the privacy concerns of these applications, we study the problem of fixed-confidence BAI under global Differential Privacy (DP) for Bernoulli distributions. While numerous asymptotically optimal BAI algorithms exist in the non-private setting, a significant gap remains between the best lower and upper bounds in the global DP setting. This work reduces this gap to a small multiplicative constant, for any privacy budget $\epsilon$. First, we provide a tighter lower bound on the expected sample complexity of any $\delta$-correct and $\epsilon$-global DP strategy. Our lower bound replaces the Kullback-Leibler (KL) divergence in the transportation cost used by the non-private characteristic time with a new information-theoretic quantity that optimally trades off between the KL divergence and the Total Variation distance scaled by $\epsilon$. Second, we introduce a stopping rule based on these transportation costs and a private estimator of the means computed using an arm-dependent geometric batching. En route to proving the correctness of our stopping rule, we derive concentration results of independent interest for the Laplace distribution and for the sum of Bernoulli and Laplace distributions. Third, we propose a Top Two sampling rule based on these transportation costs. For any budget $\epsilon$, we show an asymptotic upper bound on its expected sample complexity that matches our lower bound to a multiplicative constant smaller than $8$. Our algorithm outperforms existing $\delta$-correct and $\epsilon$-global DP BAI algorithms for different values of $\epsilon$.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization

Aurélien Bellet, Edwige Cyffers, Davide Frey, Romaric Gaudel, Dimitri Lerévérend, François Taïani

http://arxiv.org/abs/2510.17480
Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization Aurélien Bellet, Edwige Cyffers, Davide Frey, Romaric Gaudel, Dimitri Lerévérend, François Taïani http://arxiv.org/abs/2510.17480 Decentralized Learning (DL) enables users to collaboratively train models without sharing raw data by iteratively averaging local updates with neighbors in a network graph. This setting is increasingly popular for its scalability and its ability to keep data local under user control. Strong privacy guarantees in DL are typically achieved through Differential Privacy (DP), with results showing that DL can even amplify privacy by disseminating noise across peer-to-peer communications. Yet in practice, the observed privacy-utility trade-off often appears worse than in centralized training, which may be due to limitations in current DP accounting methods for DL. In this paper, we show that recent advances in centralized DP accounting based on Matrix Factorization (MF) for analyzing temporal noise correlations can also be leveraged in DL. By generalizing existing MF results, we show how to cast both standard DL algorithms and common trust models into a unified formulation. This yields tighter privacy accounting for existing DP-DL algorithms and provides a principled way to develop new ones. To demonstrate the approach, we introduce MAFALDA-SGD, a gossip-based DL algorithm with user-level correlated noise that outperforms existing methods on synthetic and real-world graphs.
1
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
Quantum Federated Learning: Architectural Elements and Future Directions

Siva Sai, Abhishek Sawaika, Prabhjot Singh, Rajkumar Buyya

http://arxiv.org/abs/2510.17642
Quantum Federated Learning: Architectural Elements and Future Directions Siva Sai, Abhishek Sawaika, Prabhjot Singh, Rajkumar Buyya http://arxiv.org/abs/2510.17642 Federated learning (FL) focuses on collaborative model training without the need to move the private data silos to a central server. Despite its several benefits, the classical FL is plagued with several limitations, such as high computational power required for model training(which is critical for low-resource clients), privacy risks, large update traffic, and non-IID heterogeneity. This chapter surveys a hybrid paradigm - Quantum Federated Learning (QFL), which introduces quantum computation, that addresses multiple challenges of classical FL and offers rapid computing capability while keeping the classical orchestration intact. Firstly, we motivate QFL with a concrete presentation on pain points of classical FL, followed by a discussion on a general architecture of QFL frameworks specifying the roles of client and server, communication primitives and the quantum model placement. We classify the existing QFL systems based on four criteria - quantum architecture (pure QFL, hybrid QFL), data processing method (quantum data encoding, quantum feature mapping, and quantum feature selection & dimensionality reduction), network topology (centralized, hierarchial, decentralized), and quantum security mechanisms (quantum key distribution, quantum homomorphic encryption, quantum differential privacy, blind quantum computing). We then describe applications of QFL in healthcare, vehicular networks, wireless networks, and network security, clearly highlighting where QFL improves communication efficiency, security, and performance compared to classical FL. We close with multiple challenges and future works in QFL, including extension of QFL beyond classification tasks, adversarial attacks, realistic hardware deployment, quantum communication protocols deployment, aggregation of different quantum models, and quantu
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 6d
The Role of Federated Learning in Improving Financial Security: A Survey

Cade Houston Kennedy, Amr Hilal, Morteza Momeni

http://arxiv.org/abs/2510.14991
The Role of Federated Learning in Improving Financial Security: A Survey Cade Houston Kennedy, Amr Hilal, Morteza Momeni http://arxiv.org/abs/2510.14991 With the growth of digital financial systems, robust security and privacy have become a concern for financial institutions. Even though traditional machine learning models have shown to be effective in fraud detections, they often compromise user data by requiring centralized access to sensitive information. In IoT-enabled financial endpoints such as ATMs and POS Systems that regularly produce sensitive data that is sent over the network. Federated Learning (FL) offers a privacy-preserving, decentralized model training across institutions without sharing raw data. FL enables cross-silo collaboration among banks while also using cross-device learning on IoT endpoints. This survey explores the role of FL in enhancing financial security and introduces a novel classification of its applications based on regulatory and compliance exposure levels ranging from low-exposure tasks such as collaborative portfolio optimization to high-exposure tasks like real-time fraud detection. Unlike prior surveys, this work reviews FL's practical use within financial systems, discussing its regulatory compliance and recent successes in fraud prevention and blockchain-integrated frameworks. However, FL deployment in finance is not without challenges. Data heterogeneity, adversarial attacks, and regulatory compliance make implementation far from easy. This survey reviews current defense mechanisms and discusses future directions, including blockchain integration, differential privacy, secure multi-party computation, and quantum-secure frameworks. Ultimately, this work aims to be a resource for researchers exploring FL's potential to advance secure, privacy-compliant financial systems.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 7d
VaultGemma: A Differentially Private Gemma Model

Amer Sinha, Thomas Mesnard, Ryan McKenna, Daogao Liu, Christopher A. Choquette-Choo, Yangsibo Huang, Da Yu, George Kaissis, Zachary Charles, Ruibo Liu, Lynn Chua, Pritish Kamath, Pasin Manurangsi, Steve He, Chiyuan ...
http://arxiv.org/abs/2510.15001
VaultGemma: A Differentially Private Gemma Model Amer Sinha, Thomas Mesnard, Ryan McKenna, Daogao Liu, Christopher A. Choquette-Choo, Yangsibo Huang, Da Yu, George Kaissis, Zachary Charles, Ruibo Liu, Lynn Chua, Pritish Kamath, Pasin Manurangsi, Steve He, Chiyuan Zhang, Badih Ghazi, Borja De Balle Pigem, Prem Eruvbetine, Tris Warkentin, Armand Joulin, Ravi KumarAmer Sinha, Thomas Mesnard, Ryan McKenna, Daogao Liu, Christopher A. Choquette-Choo, Yangsibo Huang, Da Yu, George Kaissis, Zachary Charles, Ruibo Liu, Lynn Chua, Pritish Kamath, Pasin Manurangsi, Steve He, Chiyuan Zhang, Badih Ghazi, Borja De Balle Pigem, Prem Eruvbetine, Tris Warkentin, Armand Joulin, Ravi Kumar http://arxiv.org/abs/2510.15001 We introduce VaultGemma 1B, a 1 billion parameter model within the Gemma family, fully trained with differential privacy. Pretrained on the identical data mixture used for the Gemma 2 series, VaultGemma 1B represents a significant step forward in privacy-preserving large language models. We openly release this model to the community
1 2
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 11d
Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy

Rouzbeh Behnia, Jeremiah Birrell, Arman Riasi, Reza Ebrahimi, Kaushik Dutta, Thang Hoang

http://arxiv.org/abs/2510.12908
Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy Rouzbeh Behnia, Jeremiah Birrell, Arman Riasi, Reza Ebrahimi, Kaushik Dutta, Thang Hoang http://arxiv.org/abs/2510.12908 Federated learning (FL) enables organizations to collaboratively train models without sharing their datasets. Despite this advantage, recent studies show that both client updates and the global model can leak private information, limiting adoption in sensitive domains such as healthcare. Local differential privacy (LDP) offers strong protection by letting each participant privatize updates before transmission. However, existing LDP methods were designed for centralized training and introduce challenges in FL, including high resource demands that can cause client dropouts and the lack of reliable privacy guarantees under asynchronous participation. These issues undermine model generalizability, fairness, and compliance with regulations such as HIPAA and GDPR. To address them, we propose L-RDP, a DP method designed for LDP that ensures constant, lower memory usage to reduce dropouts and provides rigorous per-client privacy guarantees by accounting for intermittent participation.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 11d
Offline and Online KL-Regularized RLHF under Differential Privacy

Yulian Wu, Rushil Thareja, Praneeth Vepakomma, Francesco Orabona

http://arxiv.org/abs/2510.13512
Offline and Online KL-Regularized RLHF under Differential Privacy Yulian Wu, Rushil Thareja, Praneeth Vepakomma, Francesco Orabona http://arxiv.org/abs/2510.13512 In this paper, we study the offline and online settings of reinforcement learning from human feedback (RLHF) with KL-regularization -- a widely used objective function in large language model alignment -- under the $\epsilon$ local differential privacy ($\epsilon$-LDP) model on the label of the human preference. In the offline setting, we design an algorithm based on the principle of pessimism and derive a new suboptimality gap of $\tilde{O}(1/[(e^\epsilon-1)^2 n])$ on the KL-regularized objective under single-policy concentrability. We also prove its optimality by providing a matching lower bound where $n$ is the sample size. In the online setting, we are the first one to theoretically investigate the problem of KL-regularized RLHF with LDP. We design an optimism-based algorithm and derive a logarithmic regret bound of $O(d_{\mathcal{F}}\log (N_{\mathcal{F}}\cdot T) /(e^\epsilon-1)^2 )$, where $T$ is the total time step, $N_{\mathcal{F}}$ is cardinality of the reward function space $\mathcal{F}$ and $d_{\mathcal{F}}$ is a variant of eluder dimension for RLHF. As a by-product of our analysis, our results also imply the first analysis for online KL-regularized RLHF without privacy. We implement our algorithm in the offline setting to verify our theoretical results and release our open source code at: https://github.com/rushil-thareja/PPKL-RLHF-Official.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 11d
Experiments & Analysis of Privacy-Preserving SQL Query Sanitization Systems

Loïs Ecoffet, Veronika Rehn-Sonigo, Jean-François Couchot, Catuscia Palamidessi

http://arxiv.org/abs/2510.13528
Experiments & Analysis of Privacy-Preserving SQL Query Sanitization Systems Loïs Ecoffet, Veronika Rehn-Sonigo, Jean-François Couchot, Catuscia Palamidessi http://arxiv.org/abs/2510.13528 Analytical SQL queries are essential for extracting insights from relational databases but concurrently introduce significant privacy risks by potentially exposing sensitive information. To mitigate these risks, numerous query sanitization systems have been developed, employing diverse approaches that create a complex landscape for both researchers and practitioners. These systems vary fundamentally in their design, including the underlying privacy model, such as k-anonymity or Differential Privacy; the protected privacy unit, whether at the tuple- or user-level; and the software architecture, which can be proxy-based or integrated. This paper provides a systematic classification of state-of-the-art SQL sanitization systems based on these qualitative criteria and the scope of queries they support. Furthermore, we present a quantitative analysis of leading systems, empirically measuring the trade-offs between data utility, query execution overhead, and privacy guarantees across a range of analytical queries. This work offers a structured overview and performance assessment intended to clarify the capabilities and limitations of current privacy-preserving database technologies.
dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · 12d
High-Probability Bounds For Heterogeneous Local Differential Privacy

Maryam Aliakbarpour, Alireza Fallah, Swaha Roy, Ria Stevens

http://arxiv.org/abs/2510.11895
High-Probability Bounds For Heterogeneous Local Differential Privacy Maryam Aliakbarpour, Alireza Fallah, Swaha Roy, Ria Stevens http://arxiv.org/abs/2510.11895 We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for one-dimensional and multi-dimensional mean estimation problems, we develop finite sample upper bounds in $\ell_2$-norm that hold with probability at least $1-\beta$. We complement these results with matching minimax lower bounds, establishing the optimality (up to constants) of our guarantees in the heterogeneous LDP regime. We further study distribution learning in $\ell_\infty$-distance, designing an algorithm with high-probability guarantees under heterogeneous privacy demands. Our techniques offer principled guidance for designing mechanisms in settings with user-specific privacy levels.
4