Age-Dependent Differential Privacy

Decisions about sharing personal information are not trivial, since there are many legitimate and important purposes for such data collection, but often the collected data can reveal sensitive information about individuals. Privacy-preserving technologies, such as differential privacy (DP), can be employed to protect the privacy of individuals and, furthermore, provide mathematically sound guarantees on the maximum privacy risk. However, they can only support informed privacy decisions, if individuals understand the provided privacy guarantees. This article proposes a novel approach for communicating privacy guarantees to support individuals in their privacy decisions when sharing data. For this, we adopt risk communication formats from the medical domain in conjunction with a model for privacy guarantees of DP to create quantitative privacy risk notifications. We conducted a crowd-sourced study with 343 participants to evaluate how well our notifications conveyed the privacy risk information and how confident participants were about their own understanding of the privacy risk. Our findings suggest that these new notifications can communicate the objective information similarly well to currently used qualitative notifications, but left individuals less confident in their understanding. We also discovered that several of our notifications and the currently used qualitative notification disadvantage individuals with low numeracy: these individuals appear overconfident compared to their actual understanding of the associated privacy risks and are, therefore, less likely to seek the needed additional information before an informed decision. The promising results allow for multiple directions in future research, for example, adding visual aids or tailoring privacy risk communication to characteristics of the individuals.

In response to the privacy leakage risks inherent in the big data processing of power user personas, propose a collaborative optimization‐based joint privacy protection mechanism for Differential Privacy (DP) and Secret Sharing (SS). This method reveals the inherent correlation between DP noise parameters and SS sharding strategy and designs an adaptive noise sharding mapping mechanism to achieve joint optimization of privacy protection and communication overhead. Based on this mechanism, a specific privacy protection scheme for power user personas is designed. Experimental results demonstrate that the DP + SS privacy protection method designed in this study achieves an accuracy rate of 93.14% on the MNIST dataset and maintains an accuracy rate of 92.06% across multiple datasets, indicating that the scheme effectively quantifies the level of privacy protection. The privacy protection level of the scheme is quantitatively defined through differential privacy budget ε ∈ [0.11,0.15], secret sharing ( k = 3, n = 5) threshold mechanism, and privacy leakage probability δ = 10 −5 . The privacy budget is dynamically allocated through the correlation between differential privacy noise variance and the minimum reconstruction threshold of secret sharing, ensuring that privacy risks are controllable and quantifiable. At the same time, the average training time for servers is about 186.4 s, which refers to the total end‐to‐end training time in a four‐server cluster environment. Compared with a single server encryption scheme, the efficiency is improved by 48.6%. The communication overhead has increased to 10.6GB, which is the total chip transmission overhead per 10,000 users. However, the calculation stability can be maintained through load balancing, indicating that the scheme has certain feasibility. The aforementioned research results not only provide a viable applied cryptographic technology solution for privacy protection in power big data but also offer new insights into balancing privacy protection strength and data availability. More importantly, the joint privacy protection mechanism proposed by the research institute can serve as a fundamental enabling technology for the infrastructure of a secure smart grid, providing quantifiable and trustworthy privacy and security guarantees for advanced data‐driven applications such as precise load prediction, demand‐side response, and collaborative optimization of distributed energy, thereby supporting the reliable and intelligent development of the smart grid.

Federated learning is a distributed machine learning technique that allows multiple devices to collaborate on learning a shared model without exchanging data. It can be used to improve model accuracy while protecting user privacy. However, traditional federated learning is vulnerable to attacks from generative adversarial networks (GANs). As a new privacy protection method, differential privacy enhances privacy protection capabilities by sacrificing some data accuracy. To optimize the privacy budget allocation scheme in traditional differential privacy, we propose a differential privacy method called ADP-FL, which dynamically adjusts the privacy budget based on Newton’s Law of Cooling. While maintaining the overall privacy budget, it dynamically tunes adaptive parameters to improve training accuracy. Additionally, we propose an asynchronous federated learning aggregation scheme that combines privacy budget with data freshness, thereby reducing the impact of differential privacy on accuracy. We conducted extensive experiments on differential privacy algorithms based on Gaussian mechanisms and Laplace mechanisms. The experimental results show that, under the same privacy budget, our algorithm achieves higher accuracy and lower communication overhead compared to the baseline algorithm.

Private record linkage (PRL) is the problem of identifying pairs of records that are similar as per an input matching rule from databases held by two parties that do not trust one another. We identify three key desiderata that a PRL solution must ensure: (1) perfect precision and high recall of matching pairs, (2) a proof of end-to-end privacy, and (3) communication and computational costs that scale subquadratically in the number of input records. We show that all of the existing solutions for PRL? including secure 2-party computation (S2PC), and their variants that use non-private or differentially private (DP) blocking to ensure subquadratic cost -- violate at least one of the three desiderata. In particular, S2PC techniques guarantee end-to-end privacy but have either low recall or quadratic cost. In contrast, no end-to-end privacy guarantee has been formalized for solutions that achieve subquadratic cost. This is true even for solutions that compose DP and S2PC: DP does not permit the release of any exact information about the databases, while S2PC algorithms for PRL allow the release of matching records. In light of this deficiency, we propose a novel privacy model, called output constrained differential privacy, that shares the strong privacy protection of DP, but allows for the truthful release of the output of a certain function applied to the data. We apply this to PRL, and show that protocols satisfying this privacy model permit the disclosure of the true matching records, but their execution is insensitive to the presence or absence of a single non-matching record. We find that prior work that combine DP and S2PC techniques even fail to satisfy this end-to-end privacy model. Hence, we develop novel protocols that provably achieve this end-to-end privacy guarantee, together with the other two desiderata of PRL. Our empirical evaluation also shows that our protocols obtain high recall, scale near linearly in the size of the input databases and the output set of matching pairs, and have communication and computational costs that are at least 2 orders of magnitude smaller than S2PC baselines.

Background: The adoption of AI in healthcare is hindered by data silos and privacy constraints, with heterogeneous sources like EHRs, wearables, and IoT devices operating in isolated ecosystems.Traditional centralized AI models fail to address interoperability while complying with regulations like HIPAA and GDPR.Federated learning (FL) has emerged as a promising decentralized alternative, but its adaptation for cross-platform healthcare data harmonization remains underexplored.Objective: This study proposes an adaptive FL framework to bridge interoperability gaps in healthcare AI, enabling secure collaboration across disparate data sources without centralized data pooling.We aim to (1) design a privacy-preserving FL architecture for heterogeneous medical data, (2) validate its interoperability using real-world EHR and wearable datasets, and (3) quantify compliance with regulatory requirements. Methods: Our framework integrates Federated Multi-Task Learning (FMTL) to handle data heterogeneity, inspired by [1]'s work on cross-institutional EHR analysis, and differential privacy (DP)enhanced aggregation, extending [2]'s approach forIoT-health data.We evaluate the system using two public datasets: (i) MIMIC-III (EHRs) and (ii) PPG-DaLiA (wearable photoplethysmography), simulating a multi-device environment.Interoperability is tested via schema mapping tools (e.g., FHIR standards), while privacy guarantees are audited using GDPR-specific metrics (e.g., data minimization, user consent logs).Results: The framework achieved 88.7% harmonization accuracy (vs.72.3% in centralized baselines) across EHR-wearable data fields, reducing semantic heterogeneity by 41% through adaptive FMTL.DP noise injection (< =1.5) maintained model utility (AUC drop < 3.2%) while ensuring compliance with HIPAA's de-identification criteria.Comparative analysis showed 23% faster convergence than conventional FL, attributed to dynamic client selection for heterogeneous devices [1].Regulatory audits confirmed adherence to GDPR's Article 35 (DPIA) and HIPAA's Safe Harbor rule.Conclusion: Adaptive FL can effectively harmonize fragmented healthcare data while preserving

As machine learning models continue to advance power consumption forecasting and smart grid analytics, concerns about privacy risks in electricity time‐series data have gained significant attention. Highlighting the unique characteristics of electricity data, such as its high periodicity and direct correlation with sensitive real‐world activities, this paper introduces a novel privacy auditing framework that systematically assesses the vulnerability of electricity forecasting models to gradient‐based data reconstruction attacks, where adversaries exploit model gradients to infer sensitive electricity usage data, posing a serious privacy risk to households, industries, and power operators. This paper introduces a novel privacy auditing framework that systematically assesses the vulnerability of electricity forecasting models to gradient‐based reconstruction attacks. Unlike traditional methods that primarily focus on privacy mitigation through model regularization or noise injection, our framework provides a quantitative evaluation of gradient leakage, allowing us to measure and analyze the extent to which adversaries can reconstruct private energy consumption data. Through experiments on benchmark electricity datasets (ETTh1, ETTh2, and ECL), we demonstrate that, without privacy‐preserving techniques, attackers can accurately reconstruct electricity consumption patterns, as indicated by the rapid decrease in mean squared error (MSE) during reconstruction iterations. However, the application of a standard defense mechanism, differential privacy (DP), significantly disrupts this process, increasing MSE and coefficient variance, thereby limiting an attacker's ability to recover meaningful energy consumption information. By formalizing the connection between gradient similarity and time‐series similarity, our study quantifies privacy risks in electricity forecasting models, and evaluates the effectiveness of DP as a representative defense mechanism. The main contribution is not an improvement to privacy‐preserving algorithms themselves, but rather the auditing framework used to measure their efficacy. Our analysis provides a quantitative framework for navigating the critical tradeoff between privacy preservation and model utility, while also considering the computational overhead of the auditing process. This work provides a systematic approach to privacy auditing, equipping researchers, policymakers, and energy providers with insights into the trade‐offs between model accuracy and data security. Future research should explore additional privacy‐preserving techniques such as homomorphic encryption, federated learning, and adversarial training to further enhance privacy protections in smart grid and energy forecasting applications.

Continuous publication of statistics collected from various location-based applications may compromise users’ privacy as the statistics could be procured from users’ private data. Differential Privacy (DP) is a new privacy notion that offers a strong privacy guarantee to all users who participate in the statistics. However, the existing DP mechanism for continuous publication of location statistics provides a privacy guarantee with the assumption that the data-points of users stream at consecutive timestamps are independent. In reality, users’ data-points may be temporally correlated, resulting in more privacy leakage due to an inadequate supply of privacy budget to the timestamps where the data-points are correlated. In this paper, we present a reformulated differential privacy definition to quantify the impact of temporal correlation on privacy leakage. Then, we introduce a privacy budget allocation method for allocating an adequate amount of privacy budget to each successive timestamps under the protection of differential privacy. Our solution adopts w-event privacy for continuously releasing statistics over infinite streams. The main idea is to check the dissimilarity between statistics at each timestamp and decide whether to publish current statistics or last release statistics. Finally, we evaluate the data utility of our proposed method by presenting experimental results for real and synthetic data sets.

Differential privacy is a precise mathematical constraint meant to ensure privacy of individual pieces of information in a database even while queries are being answered about the aggregate. Intuitively, one must come to terms with what differential privacy does and does not guarantee. For example, the definition prevents a strong adversary who knows all but one entry in the database from further inferring about the last one. This strong adversary assumption can be overlooked, resulting in misinterpretation of the privacy guarantee of differential privacy. Herein we give an equivalent definition of privacy using mutual information that makes plain some of the subtleties of differential privacy. The mutual-information differential privacy is in fact sandwiched between $\epsilon$-differential privacy and $(\epsilon,\delta)$-differential privacy in terms of its strength. In contrast to previous works using unconditional mutual information, differential privacy is fundamentally related to conditional mutual information, accompanied by a maximization over the database distribution. The conceptual advantage of using mutual information, aside from yielding a simpler and more intuitive definition of differential privacy, is that its properties are well understood. Several properties of differential privacy are easily verified for the mutual information alternative, such as composition theorems.

In the data-driven healthcare sector, balancing privacy protection and model performance is critical. This paper enhances accuracy and reliability in survival analysis by integrating differential privacy, deep learning, and the Cox proportional hazards model within a federated learning framework. Traditionally, differential privacy’s noise injection often degrades model performance. To address this, we propose two adaptive privacy budget allocation strategies considering weight changes across neural network layers. The first, LS-ADP, utilizes layer sensitivity to assess the influence of individual layer weights on model performance and develops an adaptive differential privacy algorithm. The second, ROW-DP, comprehensively assesses weight variations and absolute values to propose a random one-layer weighted differential privacy algorithm. These algorithms provide differentiated privacy protection for various weights, mitigating privacy leakage while ensuring model performance. Experimental results on simulated and clinical datasets demonstrate improved predictive performance and robust privacy protection.

The growing adoption of federated learning in marketing analytics reflects an industry-wide shift towards privacy-preserving data strategies, yet it also presents a critical trade-off between data granularity and consumer trust. This paper explores how differential privacy techniques affect the fidelity of insights drawn from consumer behavior data while mitigating privacy risks in federated environments. We examine the extent to which granular data can be retained without compromising consumer anonymity, and how varying privacy budgets impact model accuracy and stakeholder trust. Through an interdisciplinary approach combining computational experiments, privacy risk modeling, and consumer perception analysis, we evaluate how organizations can balance the utility of detailed marketing analytics with ethical data stewardship. Our findings reveal that while fine-grained data significantly improves personalization and campaign targeting, consumer trust declines when privacy guarantees are weak or opaque. We propose a calibrated differential privacy mechanism integrated with federated learning to optimize this trade-off, offering a framework for achieving both regulatory compliance and strategic marketing outcomes. The paper contributes to ongoing debates on responsible AI, data governance, and trust in digital ecosystems.

Privacy preserving data releasing is an important problem for reconciling data openness with individual privacy.The state-of-the-art approach for privacy preserving data release is differential privacy, which offers powerful privacy guarantee without confining assumptions about the background knowledge about attackers.For genomic data with huge-dimensional attributes, however, current approaches based on differential privacy are not effective to handle.Specifically, amount of noise is required to be injected to genomic data with tens of million of SNPs (Single Nucleotide Polymorphisms), which would significantly degrade the utility of released data.To address this problem, this paper proposes a differential privacy guaranteed genomic data releasing method.Through executing belief propagation on factor graph, our method can factorize the distribution of sensitive genomic data into a set of local distributions.After injecting differential-privacy noise to these local distributions, synthetic sensitive data can be obtained by sampling on noise distribution.Synthetic sensitive data and factor graph can be further used to construct approximate distribution of non-sensitive data.Finally, non-sensitive genomic data is sampled from the approximate distribution to construct a synthetic genomic dataset.

Differential privacy is a privacy model that has become quite popular because of the strong privacy guarantees it provides. Differential privacy was initially stated as a privacy guarantee in an interactive setting, where queries are submitted to a database containing the original individual records. However, it is general enough to deal with microdata releases. The principle underlying differential privacy is that the presence or absence of any single individual record in the database or data set should be unnoticeable when looking at the responses returned for the queries.

Differential privacy in probabilistic systems

The software-based implementation of differential privacy mechanisms has been shown to be neither friendly for lightweight devices nor secure against side-channel attacks. In this work, we aim to develop a hardware-based technique to achieve differential privacy by design. In contrary to the conventional software-based noise generation and injection process, our design realizes local differential privacy (LDP) by harnessing the inherent hardware noise into controlled LDP noise when data is stored in the memory. Specifically, the noise is tamed through a novel memory design and power downscaling technique, which leads to double-faceted gains in privacy and power efficiency. A well-round study that consists of theoretical design and analysis and chip implementation and experiments is presented. The results confirm that the developed technique is differentially private, saves 88.58% system power, speeds up software-based DP mechanisms by more than <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$10^{6}$</tex-math></inline-formula> times, while only incurring 2.46% chip overhead and 7.81% estimation errors in data recovery.

Dynamic consent management allows a data subject to dynamically govern her consent to access her data. Clearly, security and privacy guarantees are vital for the adoption of dynamic consent management systems. In particular, specific data protection guarantees can be required to comply with rules and laws (e.g., the General Data Protection Regulation (GDPR)). Since the primary instantiation of the dynamic consent management systems in the existing literature is towards developing sustainable e-healthcare services, in this paper, we study data protection issues in dynamic consent management systems, identifying crucial security and privacy properties and discussing severe limitations of systems described in the state of the art. We have presented the precise definitions of security and privacy properties that are essential to confirm the robustness of the dynamic consent management systems against diverse adversaries. Finally, under those precise formal definitions of security and privacy, we have proposed the implications of state-of-the-art tools and technologies such as differential privacy, blockchain technologies, zero-knowledge proofs, and cryptographic procedures that can be used to build dynamic consent management systems that are secure and private by design.