Flexible privacy model for linear queries improves privacy and utility tradeoff.
problem Balancing privacy across different attributes in sensitive datasets.
method Developed a systematic procedure to adapt existing differentially private mechanisms to dX-privacy for linear queries. result Improved privacy and utility tradeoff through flexible privacy budgets.
Privacy-preserving dropout technique for neural networks.
problem Overfitting in deep neural networks and privacy of training data.
method Modified variational dropout with concentrated differential privacy.
result The technique provides differential privacy for neural networks.
This work improves federated learning privacy and accuracy with non-private data sharing and approximate gradient coding.
problem Challenges of non-IID data and stragglers in federated learning.
method Data-driven strategy combining offline data sharing and approximate gradient coding.
result Achieves a trade-off between privacy and utility, leading to improved model convergence and accuracy.
Secure transfer learning framework improves model flexibility without compromising privacy.
problem Scattered data across organizations limits machine learning.
method Federated Transfer Learning (FTL) framework with secure transfer cross validation.
result Models can be built more flexibly and accurately with shared labels from different sources.
This paper bounds min-entropy leakage for Blowfish privacy using graph symmetries.
problem Bounding min-entropy leakage for Blowfish privacy mechanisms.
method Organizing analysis over symmetrical partitions corresponding to orbits of graph automorphism groups.
result Demonstrates a construction meeting the bound with asymptotic equality, showing tightness.
A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of Gaussian processes (GPs). We propose a method using GPs to provide differentially priva…
KNG mechanism provides sanitized statistical summaries with strong privacy and utility guarantees.
problem Producing sanitized statistical summaries with differential privacy.
method Promotes summaries that minimize an objective function by weighting gradients, achieving utility similar to objective perturbation but with stronger privacy guarantees.
result KNG's noise is asymptotically negligible compared to statistical error for many problems.
RUCA maximizes data utility while minimizing privacy risk.
problem Privacy breaches in big data applications.
method RUCA (Ratio Utility and Cost Analysis) for privacy-preserving data projection.
result RUCA significantly outperforms existing methods in minimizing privacy risk.
Enhances privacy in machine learning through Rényi Pufferfish mechanisms.
problem Designing general and efficient Pufferfish mechanisms that maintain privacy and utility.
method Introduces a Rényi divergence-based variant of Pufferfish, generalizes the Wasserstein mechanism, and proves privacy amplification results.
result Extends the applicability of Pufferfish framework and provides stronger privacy guarantees.
Paper simplifies DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.
problem Tension between efficiency and flexibility in DP composition theorems.
method Rényi Differential Privacy (RDP) for adaptive privacy budgets, proving simpler composition theorem with smaller constants.
result Practical DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.
FLORAS uses orthogonal sequences for SISO FL, offering both DP and convergence guarantees.
problem Privacy-preserving wireless federated learning in SISO systems.
method Leverages orthogonal sequences to eliminate CSIT requirement and provide DP guarantees.
result FLORAS achieves a smooth tradeoff between convergence rate and DP levels.
New framework for DP-SMO with near-optimal privacy-loss trade-off.
problem Optimal trade-off between privacy and population loss in DP-SMO.
method General framework using Phased-ERM method and black-box optimization.
result Near-linear time algorithms with near-optimal guarantees.
The paper proposes methods to infer from privacy-protected data using simulation-based techniques.
problem Valid statistical inference from privacy-protected data is computationally challenging.
method Simulation-based inference methods, including sequential Monte Carlo and neural conditional density estimators.
result Valid statistical inferences can be made from privacy-protected data.
A framework for private causal effect estimation without structural assumptions.
problem Estimating causal effects from private observational data.
method Model-agnostic framework that privatizes predictions and aggregation steps.
result Maintains competitive performance under realistic privacy budgets.
New algorithms protect user data while optimizing personalized decisions.
problem Personalized decision-making with private user data.
method Developed LDP algorithms for stochastic generalized linear bandits using SGD and OLS.
result Achieved the same regret bound as non-privacy settings with LDP.
Secure Multiparty Computation protects data privacy in Symbolic Regression.
problem Data privacy in Symbolic Regression models.
method Secure Multiparty Computation for vertical partitioning.
result Comparable performance to centralized model while preserving privacy.
Paper addresses privacy threats in real-time SMs data.
problem Privacy threats from real-time SMs data.
method Information-theoretic privacy measure, deep learning adversarial framework.
result Proposes a privatization mechanism with minimal distortion.
FedLog reduces communication in federated learning by sharing data summaries.
problem Significant communication overhead in federated learning with large model parameters.
method Shares minimal sufficient statistics via Bayesian inference and differential privacy.
result High learning accuracy with low communication overhead.
d3p package enables efficient Bayesian inference with differential privacy.
problem Efficiently performing Bayesian inference under differential privacy constraints.
method Differentially private variational inference for flexible probabilistic models.
result Achieves significant speed-up in runtime for complex models.
The exponential mechanism is extended to infinite dimensional outputs, leading to a Central Limit Theorem and a non-negligible privacy noise.
problem Extending the exponential mechanism to infinite dimensional outputs for privacy and statistical estimation.
method Designing the exponential mechanism with respect to a specific base measure over the output space, and proving a Central Limit Theorem.
result The magnitude of privacy noise is asymptotically non-negligible relative to the statistical estimation error.
Develops a new deep learning framework for privacy-preserving text representations.
problem Privacy concerns in deep learning frameworks requiring data pooling to a trusted server.
method Three modules: embedding, randomization, and classifier. Novel LDP protocol reduces privacy impact on accuracy.
result Framework delivers comparable or better performance than non-private and existing LDP protocols.
A practical one-shot federated learning algorithm for cross-silo setting.
problem Limited applicability of existing one-shot federated learning algorithms due to specific model support and lack of privacy guarantees.
method FedKT, a one-shot federated learning algorithm that supports any classification models and provides differential privacy guarantees.
result FedKT significantly outperforms other state-of-the-art federated learning algorithms with a single communication round.
DiPriMe forests use private medians to create balanced tree splits for privacy-protected data.
problem Privacy concerns in training random forests due to multiple data queries.
method Proposes DiPriMe forests, which use a private median to generate balanced splits, ensuring differential privacy.
result DiPriMe forests achieve high utility while maintaining differential privacy, as shown both theoretically and empirically.
Paper proposes a privacy-preserving method for estimating complex models.
problem Lack of flexibility in existing model classes for approximating data-generating processes.
method Privacy-preserving distributed estimation of generalized additive mixed models using component-wise gradient boosting.
result Proposed algorithm yields equivalent model estimates as component-wise gradient boosting on pooled data.
First certified defense scaling to large datasets and models.
problem Robustness against adversarial examples in machine learning models.
method PixelDP, based on differential privacy.
result First certified defense that scales to large networks and models.
CFL clusters clients to improve Federated Learning performance.
problem Suboptimal results in FL when client data distributions diverge.
method Exploits geometric properties of FL loss surface to cluster clients.
result CFL achieves greater or equal performance than conventional FL.
Differentially private conformal prediction improves statistical efficiency.
problem Quantifying uncertainty in private data analysis.
method Introducing differential conformal prediction and developing Differentially Private Conformal Prediction (DPCP).
result DPCP produces tighter prediction sets than existing private split conformal approaches.
Data-dependent PAC-Bayes priors via differential privacy improve generalization bounds.
problem Creating valid generalization bounds for unknown data distributions.
method Using ε-differential privacy to construct data-dependent priors, leading to valid PAC-Bayes bounds.
result Data-dependent priors via differential privacy yield nonvacuous generalization bounds.
New framework UIFV reconstructs private features in VFL without model details.
problem Privacy risks in VFL where adversaries can reconstruct sensitive features.
method Unified InverNet Framework (UIFV) that uses intermediate feature data.
result Significantly outperforms state-of-the-art techniques in attack precision.
Federated learning improves by training central model with client model outputs.
problem Direct averaging of client models is limited in FL.
method Ensemble distillation for model fusion.
result Central model trained faster with fewer communication rounds.
Framework extracts symptoms from EHRs for rapid disease outbreak detection.
problem Extracting relevant data from unstructured medical texts.
method Conformal active learning for efficient data mining.
result Framework achieves strong performance with minimal manual labeling.
Proposes a transfer learning framework for sparse SIMs without raw source data.
problem Lack of direct access to raw source data and known link functions in transfer learning.
method Source-data-free framework based on SIM, using summary statistics and a multilayer perceptron.
result Consistent improvements over existing approaches in synthetic and real-world data.
New method for private learning with public features improves convergence rates.
problem Private estimation with public features under local differential privacy.
method Semi-feature LDP, HistOfTree estimator.
result HistOfTree reaches mini-max optimal convergence rate.
Framework generates private synthetic data for unlabeled mixed-type data.
problem Generating private synthetic data for unlabeled mixed-type data.
method Combines autoencoders and GANs for differential privacy.
result Learned model generates synthetic data with similar statistical properties.
Federated learning for Bayesian network structure learning across distributed data.
problem Learning Bayesian network structure from horizontally partitioned data across different parties.
method Distributed structure learning using continuous optimization (ADMM).
result Improved performance compared to other methods, especially with many clients and limited data.
Proposes elliptical transformation for improving machine learning performance in perturbation models.
problem Performance degradation of machine learning techniques in transform domain due to feature pattern differences.
method Introduces a nonlinear parametric perturbation model that transforms input feature patterns to elliptical patterns, and applies flexible block-wise dimensionality reduction.
result The proposed method outperforms PCA in classification performance and data privacy protection.
Unified framework for learning flexible probabilistic programs using DPP and PAC-Bayes bounds.
problem Learning and generalizing from complex probabilistic models.
method Unified DPP representation and PAC-Bayes bounds for stochastic programs.
result Improved performance and generalization prediction using flexible DPP model representations and learned complexity measures.
Improves privacy amplification by shuffling for differential privacy.
problem Enhancing privacy guarantees in systems with anonymous data contributions.
method Theoretical and numerical analysis of Rényi differential privacy parameters and privacy amplification by shuffling.
result First asymptotically optimal analysis of Rényi differential privacy parameters for shuffled outputs.
Proposes a privacy-preserving recommendation system using matrix factorization and differential privacy.
problem Privacy leakage in recommendation systems when anonymizing user data is not sufficient.
method Uses matrix factorization and differential privacy via the Gaussian mechanism.
result Demonstrates excellent utility for privacy-preserving recommendation systems.
Federated learning with Bayesian differential privacy offers improved privacy and accuracy.
problem Privacy in federated learning with similar data distributions.
method Bayesian differential privacy for federated learning, with improved privacy budgeting.
result Significant advantage over state-of-the-art privacy bounds, with lower noise and improved accuracy.
Paper introduces CWDAE for better synthetic data generation.
problem Measuring discrepancy between generative and ground-truth distributions.
method Introduces mixture Cramer-Wold distance for joint and marginal distributional learning.
result CWDAE shows remarkable performance in generating synthetic data.
This work optimizes mean estimation under varying privacy constraints.
problem Mean estimation with heterogeneous privacy constraints.
method Proposes an algorithm for mean estimation under different privacy levels for users.
result Shows a saturation phenomenon in performance as privacy levels are relaxed.
Improves privacy guarantees by analyzing randomness in privacy-preserving mechanisms.
problem Balancing user privacy and business constraints in privacy-preserving mechanisms.
method Analyzes explicit and implicit randomness in privacy mechanisms and proposes a probabilistic calibration method.
result Proposes privacy at risk, providing stronger privacy guarantees with quantifiable risks.
The paper evaluates privacy in differential privacy machine learning, finding large gaps between guarantees and practical utility.
problem Lack of understanding and control over privacy and utility trade-offs in differential privacy machine learning.
method Experiments with logistic regression and neural networks to quantify privacy impact and compare different mechanisms.
result There is a significant gap between privacy guarantees and practical utility in differential privacy machine learning.
The paper analyzes and proposes methods for privately sharing individual privacy losses using per-instance differential privacy.
problem The standard differential privacy framework provides a worst-case bound that may not accurately reflect individual privacy losses.
method The paper analyzes per-instance differential privacy and proposes methods to privately and accurately publish per-instance privacy losses.
result The methods privately and accurately publish per-instance differential privacy losses with minimal additional privacy cost.
This work optimizes mean estimation under varying user privacy demands.
problem Mean estimation with heterogeneous privacy levels.
method Proposes an algorithm that is minimax optimal and has near-linear run-time.
result Privacy requirements of the most stringent users dictate overall error rates.
A new privacy accountant for Gaussian differential privacy measures individual privacy losses.
problem Bounding differential privacy loss for each participant in data analysis.
method Developed a privacy accountant for adaptive compositions of randomised mechanisms using Gaussian differential privacy.
result Provided optimal bounds for the Gaussian mechanism and constructed an approximative individual privacy accountant.
Paper improves deep learning privacy with new f-differential privacy framework.
problem Training neural networks on sensitive data while maintaining privacy.
method Introduced and analyzed f-differential privacy for neural networks training. result Improved privacy guarantees for neural networks training without sacrificing accuracy.