The study introduces a holdout-based framework to assess synthetic data fidelity and privacy.
problem Evaluating the quality and privacy of synthetic data solutions for mixed-type tabular data.
method Holdout-based empirical assessment framework measuring fidelity and privacy risk.
result Synthetic data samples are as close to the training as to the holdout data, indicating generalization and independence from individual records.
This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on intermediate outputs.
problem The exposure of intermediate results in hidden layers of deep computer vision models poses significant privacy concerns.
method The approach leverages Degrees of Freedom (DoF) to evaluate the amount of information retained in each layer and combines this with the rank of the Jacobian matrix to assess sensitivity to input variations.
result The proposed framework provides deeper insights into privacy risks associated with intermediate representations without requiring adversarial attack simulations.
New method assesses individual training points' privacy risk without retraining.
problem Privacy vulnerability of individual training points in membership inference attacks.
method Derives a closed-form decomposition of individual black-box MIA vulnerability, extending to deep networks.
result Proposes a surrogate score operating on last-layer representations that requires only a single trained model.
Paper assesses the market value of sharing privacy-protected smart meter data.
problem Value of sharing privacy-protected smart meter data between consumers and load serving entities.
method Discounted differential privacy model, ANN-based load forecasting, optimal procurement problem.
result Significant value in sharing smart meter data while retaining individual consumer privacy.
Introduces six levels of privacy for financial synthetic data.
problem Privacy risks in financial synthetic data.
method Defines six levels of privacy protection for synthetic data.
result Provides a framework to assess and improve privacy in synthetic data.
New auditors assess f-DP privacy with adaptive sampling, avoiding large sample sizes.
problem Empirical auditing of f-DP privacy with adaptive sampling. method Shift focus to f-DP, develop adaptive auditors for whitebox and blackbox settings. result Adaptive auditors detect f-DP violations across the privacy spectrum with statistical guarantees. Synthetic data improves credit scoring models' performance without compromising borrower privacy.
problem Scarcity of real data for credit scoring models due to privacy concerns.
method Privacy-preserving training with synthetic data.
result Credit scoring models trained with synthetic data show a reduction of 3% in AUC and 6% in KS compared to real data models.
In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset. We use generative adversarial network to draw privacy-preserving artificial data samples and derive an empirical method to assess the risk of infor…
Optimal privacy-preserving ranking from noisy comparisons.
problem Protecting individual privacy in ranking from noisy comparisons.
method Differentially private ranking algorithms under edge and individual differential privacy.
result Achieved minimax optimal rates of convergence under privacy constraints.
In this paper, we propose FedGP, a framework for privacy-preserving data release in the federated learning setting. We use generative adversarial networks, generator components of which are trained by FedAvg algorithm, to draw privacy-preserving artificial data samples and empirically assess the risk of information dis…
Framework audits synthetic datasets for trustworthiness across various use cases.
problem Assessing the trustworthiness of synthetic datasets and models.
method Holistic auditing framework focusing on bias, fidelity, utility, robustness, and privacy.
result Introduces a trustworthiness index and model selection process for controllable trade-offs.
Improved canary crafting for one-run privacy auditing reduces leakage estimates.
problem Detecting canaries in one-run privacy auditing to estimate leakage effectively.
method Optimizes canaries for detectability and diversity, using a greedy initialization and bilevel optimization.
result Achieves stronger leakage estimates at lower computational cost.
Log-Loss scores expose membership privacy breaches.
problem Privacy leakage from statistical aggregates like Log-Loss scores.
method Proved that Log-Loss scores enable full accuracy membership inference in a single query.
result Complete membership privacy breach is possible with Log-Loss scores.
Develops privacy-preserving methods for equivalence testing in healthcare.
problem Protecting patient data in healthcare studies.
method Differential privacy techniques for simulation-based calibration.
result Maintains type-I error control and comparable power to non-private methods.
Paper presents a privacy-preserving algorithm for estimating peer effects using the Ising model.
problem Privacy concerns in estimating peer effects using network data.
method Developed a (ε,δ)-differentially private algorithm using Ising model. result Established regret bounds and validated performance on synthetic and real-world networks.
Developed a new method to generate synthetic data while protecting privacy.
problem Protecting privacy of human participant data while making it publicly accessible.
method A multi-step framework based on Classification and Regression Trees and an original distance-based filtering.
result Satisfactory protection against attribute disclosure attacks and formal prevention of membership disclosure attacks.
New method calibrates noise for attack risk, improving ML model accuracy.
problem Improving accuracy of privacy-preserving ML models while maintaining privacy.
method Directly calibrates noise scale to a desired attack risk level, bypassing the standard ε-calibration. result Significantly decreases noise scale, leading to increased utility at the same risk level.
The paper explores how to measure and optimize ad reach while maintaining user privacy.
problem Measuring ad reach while preserving user privacy in online advertising.
method Introduces k-anonymity and probabilistic discounting for frequency capping. result Privacy introduces a significant performance drop but with manageable costs.
Synth-MIA assesses privacy leakage in synthetic tabular data models.
problem Challenges in evaluating privacy leakage in synthetic tabular data.
method Unified threat framework deploying multiple attacks.
result Higher synthetic data quality correlates with greater privacy leakage.
FedRD improves risk difference estimation in federated learning for clinical outcomes.
problem Privacy-preserving model co-training in medical research is hindered by server-dependent architectures and focus on relative effect measures.
method FedRD is a server-independent, communication-efficient framework for federated risk difference estimation in distributed survival data.
result FedRD provides valid confidence intervals and hypothesis testing, and is asymptotically equivalent to pooled individual-level analysis.
Paper evaluates synthetic retail data for fidelity, utility, and privacy.
problem Ensuring accurate synthetic data in retail.
method Differentiates between continuous and discrete data, measures fidelity and utility, and uses Differential Privacy for privacy.
result Validated framework for reliable and scalable synthetic data evaluation.
BIF assesses feature importance using Dirichlet distribution and Bayesian inference.
problem Quantitative feature importance assessment in statistical models.
method Utilizes Dirichlet distribution for probabilistic feature importance assessment via approximate Bayesian inference.
result Learned importance provides relative significance and confidence quantification of features.
Study evaluates federated learning with differential privacy on MIMIC-III, improving model performance with careful parameter tuning.
problem Training machine learning models on privacy-sensitive data sets locked in healthcare facilities.
method Extensive evaluation of federated and differential privacy techniques on MIMIC-III dataset, analyzing various parameters.
result Careful parameter tuning is crucial for federated learning with differential privacy, especially for data distribution and communication strategies.
Voice-enabled interactions provide more human-like experiences in many popular IoT systems. Cloud-based speech analysis services extract useful information from voice input using speech recognition techniques. The voice signal is a rich resource that discloses several possible states of a speaker, such as emotional sta…
TAMIS improves MIA on synthetic data, reducing cost and requiring less knowledge.
problem Empirical assessment of privacy in machine learning algorithms.
method Improves MAMA-MIA by recovering graphical model from synthetic data and introducing a more accurate attack score.
result TAMIS achieves better or similar performance to MAMA-MIA on synthetic data challenges.
This paper analyzes FL privacy risks and defensive strategies.
problem Privacy leakage in federated learning.
method Literature review of attack methods and defensive strategies.
result No single defensive strategy is sufficient for all attacks.
We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being sha…
This paper introduces DPI, a new metric to assess data-copying risk in tabular data.
problem Measuring privacy risk of data-copying in tabular generative models.
method Proposes Data Plagiarism Index (DPI) for evaluating data-copying risk.
result DPI identifies data-copying threats to tabular data models, highlighting privacy and fairness issues.
Optimal testing for densities under local differential privacy constraints.
problem Testing goodness-of-fit for densities under privacy constraints.
method Estimation of quadratic distance and minimax separation rates.
result First minimax optimal test under local differential privacy constraints.
Privacy-preserving synthetic data from EHRs for learning and inference.
problem Sharing sensitive EHR data while maintaining patient privacy.
method Differentially private normalizing flows for density estimation and variational inference.
result Privacy-preserving synthetic data can yield good utility at a reasonable privacy cost.
Study shows privacy and utility trade-offs in synthetic data models, impacting fairness and real-world performance.
problem Understanding the impact of differential privacy on fairness and model performance in synthetic data.
method Systematic analysis of differentially private synthetic datasets on classification models, measuring utility and bias using fairness metrics.
result More privacy does not necessarily mean more bias, but it can affect model performance when deployed on real data.
Study quantized models' privacy against membership inference attacks.
problem Privacy risk in quantized machine learning models.
method Proposed a new MIS indicator for post-training quantization procedures, minimizing empirical loss.
result Demonstrated effectiveness of new MIS indicator in assessing and ranking privacy risk.
Eye tracking is handled as one of the key technologies for applications that assess and evaluate human attention, behavior, and biometrics, especially using gaze, pupillary, and blink behaviors. One of the challenges with regard to the social acceptance of eye tracking technology is however the preserving of sensitive …
Gen-LRA attacks synthetic data leakage without model knowledge.
problem Auditing synthetic data privacy leakage.
method Generative Likelihood Ratio Attack (Gen-LRA).
result Gen-LRA outperforms other attacks across metrics.
ARF synthesizes epidemiological data to match original findings.
problem Synthetic data quality and privacy in epidemiology.
method Adversarial Random Forests (ARF) for efficient data synthesis.
result ARF-generated synthetic data consistently matches original epidemiological findings.
Deep learning models have demonstrated high-quality performance in areas such as image classification and speech processing. However, creating a deep learning model using electronic health record (EHR) data, requires addressing particular privacy challenges that are unique to researchers in this domain. This matter foc…
Mobility datasets are fundamental for evaluating algorithms pertaining to geographic information systems and facilitating experimental reproducibility. But privacy implications restrict sharing such datasets, as even aggregated location-data is vulnerable to membership inference attacks. Current synthetic mobility data…
Proposes a game-theoretic framework for ML trust regulation.
problem Lack of coordination between ML model builders and regulators.
method Formulates trustworthy ML as a multi-objective multi-agent optimization problem and introduces regulation games and ParetoPlay.
result Enables efficient enforcement of ML model specifications without discouraging participation.
DAISYnt evaluates synthetic data quality and privacy in regulated domains.
problem Balancing data quality and privacy in regulated domains.
method Developed a suite of advanced tests (DAISYnt) to evaluate synthetic data quality and privacy.
result DAISYnt sets a de facto standard for synthetic data evaluation in regulated domains.
Hierarchical Federated Learning bounds generalize using Wasserstein distance.
problem Bounding generalization error in Federated Learning with hierarchical sampling.
method Introduced a hierarchical sampling framework and derived generalization bounds using Wasserstein distance.
result Recover and strictly imply existing CMI bounds for bounded losses.
Improved federated learning methods for privacy and efficiency.
problem Privacy and efficiency trade-offs in federated learning.
method FedHybrid and FedNewton: improved federated learning algorithms.
result Achieved comparable accuracy to FedSGD with fewer communication rounds.
Paper proposes a new method to assess synthetic data generators.
problem Assessing the quality of implicit generative models.
method Kernelised Stein Statistic (KSD) test based on non-parametric Stein operator.
result Improved power performance compared to existing approaches.
Federated survival analysis outperforms local and centralized training, with RSF offering the best balance of discrimination, calibration, and robustness.
problem Survival analysis models require large, diverse cohorts but are limited by privacy regulations and lack of centralized data.
method Federated learning (FL) is used to train shared models without exchanging raw data.
result FL consistently outperforms local training and approaches, and occasionally exceeds centralized performance.
New framework evaluates MIA without retraining, addressing biases.
problem Evaluate MIA without retraining and under distribution shift.
method Causal inference approach to MIA evaluation.
result Practical estimators for MIA metrics without retraining.
Develops a framework to assess systemic risk in the economy using bank-firm network data.
problem Measuring systemic risk in the economy using multilayer network data.
method Unified framework combining techniques to reconstruct multilayer economy structure from bank and firm balance sheets, and dynamics of shock propagation.
result Identifies systemically important firms and banks, and assesses systemic risk determinants.
We present a proxy dataset of vital signs with class labels indicating patient transitions from the ward to intensive care units called Ward2ICU. Patient privacy is protected using a Wasserstein Generative Adversarial Network to implicitly learn an approximation of the data distribution, allowing us to sample synthetic…
New method detects if data points were used in training models with low cost and high power.
problem Detecting if a particular data point was used in training a model.
method Fine-grained modeling of null hypothesis in likelihood ratio tests, leveraging reference models and population data.
result RMIA has superior test power compared to prior methods, even at extremely low false positive rates.
Adaptive kernel approach learns causal effects from diverse data sources.
problem Learning causal effects from multiple, decentralized data sources in a federated setting.
method Adaptive transfer algorithm using Random Fourier Features to estimate similarities and disentangle loss function components.
result Empirically outperforms baselines on decentralized data sources with different distributions.