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.
Proposes a new privacy notion for membership inference attacks on machine learning models.
problem Membership inference attacks on machine learning models.
method Introduces f-Membership Inference Privacy (f-MIP) and μ-Gaussian Membership Inference Privacy (μ-GMIP) to quantify and mitigate privacy risks. result Analyzes likelihood ratio-based attacks and derives μ-GMIP guarantees for stochastic gradient descent (SGD) models. This paper analyzes how differential privacy and data skewness affect membership inference attacks.
problem Membership inference attacks on privately trained models.
method Developed MPLens system to evaluate membership inference vulnerability.
result Membership inference risk is higher with skewed training data and differential privacy has trade-offs.
Paper presents a fast, private MH algorithm for large-scale Bayesian inference.
problem Privacy-preserving Bayesian inference for large-scale data.
method Developed a novel DP-MH algorithm using minibatches.
result First exact and fast DP MH algorithm with privacy, scalability, and efficiency trade-offs.
Noise-aware Bayesian inference framework for locally private data collection.
problem Privacy-preserving data collection with non-trustworthy aggregators.
method Noise-aware probabilistic modeling framework for Bayesian inference under LDP.
result Demonstrated efficacy in parameter estimation for various distributions and regression models.
Unified framework analyzes privacy risks from gradients in distributed learning.
problem Analyzing inference privacy risks from gradients in machine learning.
method Unified game-based framework for various attacks, including attribute, property, distributional, and user disclosures.
result Demonstrates inefficacy of data aggregation for privacy against inference attacks.
New method improves privacy risk evaluation of machine learning models.
problem Machine learning models can be vulnerable to membership inference attacks.
method Proposed new inference attack method based on prediction entropy, and introduced privacy risk score metric.
result Existing defense approaches are not as effective as previously reported.
Paper proposes a privacy-preserving knockoff inference method.
problem Ensuring privacy in model-X knockoff inference.
method Differential privacy framework for knockoff inference.
result Guaranteed FDR control with privacy protection.
A new method for privacy-preserving Bayesian learning in federated learning.
problem Privacy-preserving learning of models from distributed sensitive data.
method Differentially private partitioned variational inference (DPVI) for federated learning.
result First general framework for federated Bayesian learning with differential privacy.
Generative text classifiers are most vulnerable to membership inference attacks.
problem Privacy threat from Membership Inference Attacks on generative text classifiers.
method Comprehensive empirical evaluation of generative, discriminative, and pseudo-generative classifiers across various datasets.
result Generative classifiers explicitly modeling P(X,Y) are most vulnerable to membership leakage. 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.
Paper presents privacy-preserving techniques for HD computing.
problem Privacy loss in HD computing due to reversible computation.
method Quantization and pruning of hypervectors for differential privacy.
result Differentially private HD model for cloud inference.
New defense DMP preserves ML model utility while enhancing membership privacy.
problem Membership inference attacks (MIAs) on machine learning models.
method Knowledge distillation to train ML models with membership privacy.
result DMP provides significantly better tradeoffs between membership privacy and classification accuracies.
Proposes MIP, a privacy notion that requires less randomness than DP, leading to better utility.
problem Preserving privacy in machine learning models with sensitive data.
method Introduces membership inference privacy (MIP) as a new privacy notion and shows its relationship with differential privacy (DP).
result MIP can be achieved with less randomness than DP, resulting in better utility.
Principled mapping from pure-DP ε to GDP μ for Gaussian differential privacy
problem Choosing the μ parameter in Gaussian differential privacy
method Matching the worst-case success of a membership inference attack
result Recommendation of μ ≈ ε/5 as a conservative general-purpose conversion
Machine unlearning can compromise privacy, study shows.
problem Machine unlearning may leave data imprints in ML models, risking privacy.
method Proposed a membership inference attack to detect leakage.
result Machine unlearning can lead to unintended privacy risks.
Noise injection improves inference privacy in DNN models.
problem Malicious servers can infer sensitive attributes from input data.
method Adaptive Noise Injection (ANI) using a lightweight DNN on the client.
result Significant improvement in privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy).
Many machine learning applications are based on data collected from people, such as their tastes and behaviour as well as biological traits and genetic data. Regardless of how important the application might be, one has to make sure individuals' identities or the privacy of the data are not compromised in the analysis.…
Privacy-preserving inference for clinical trials using differential privacy.
problem Balancing knowledge sharing and privacy in healthcare data.
method Differential privacy (DP) applied to log-linear belief updates in distributed settings.
result Differentially private, distributed inference methods outperform existing techniques.
New framework for privacy-preserving statistical inference using robust statistics.
problem Privacy-preserving statistical inference with robust statistics.
method Introducing a general framework for parametric inference with differential privacy guarantees using M-estimators and test statistics.
result Demonstrated that differential privacy is weaker than robustness and can be achieved by randomizing robust M-estimators.
New MCMC method estimates differential privacy from multiple MIAs without worst-case assumptions.
problem Bayesian estimation of differential privacy from membership inference attacks.
method Bayesian estimation via MCMC algorithm (MCMC-DP-Est).
result More cautious privacy analysis with joint estimation of MIA strengths and privacy parameter.
Regularization can improve both privacy and performance in machine learning models.
problem Privacy vs. Utility trade-off in machine learning models.
method The study uses logistic regression with ridge regularization and a leave-one-out analysis tool.
result Increasing the number of parameters can improve both privacy and performance when coupled with proper regularization.
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.
This paper protects rankings from differential privacy breaches.
problem Leakage of personal information in rankings.
method Develops ε-ranking differential privacy and a multistage ranking algorithm.
result Establishes the connection between Mallows model and ε-ranking differential privacy.
Paper bridges statistical inference for DP-SGD, a privacy-preserving machine learning method.
problem Asymptotic statistical inference for Differentially Private Stochastic Gradient Descent (DP-SGD).
method Established asymptotic properties of SGD under randomized subsampling, extended to DP-SGD, proposed methods for constructing valid confidence intervals.
result Valid confidence intervals for DP-SGD output achieve nominal coverage rates while maintaining privacy.
Causal models offer stronger privacy guarantees and better generalization than associational models in machine learning.
problem Privacy attacks on machine learning models, especially membership inference attacks.
method Demonstrated the benefit of causal learning in machine learning models, showing better generalization and stronger privacy guarantees.
result Causal models provide stronger differential privacy guarantees and are more robust to membership inference attacks compared to associational models.
PASE method protects machine learning models from membership inference attacks without significant accuracy loss.
problem Membership inference attacks on machine learning models.
method Switching ensembles approach to mitigate privacy leakage.
result PASE method provides effective privacy protection with minimal accuracy penalty.
APGE protects graph node representations from inference attacks.
problem Privacy leakage in graph embedding methods.
method Adversarial training framework with disentangling and purging mechanisms.
result APGE preserves structural and utility attributes while concealing private information.
Bayesian inference has great promise for the privacy-preserving analysis of sensitive data, as posterior sampling automatically preserves differential privacy, an algorithmic notion of data privacy, under certain conditions (Dimitrakakis et al., 2014; Wang et al., 2015). While this one posterior sample (OPS) approach e…
Proposes a private empirical bootstrap for Gaussian Differential Privacy.
problem Quantifying uncertainty in massive data under Differential Privacy.
method Gaussian Differential Private Bootstrap by Subsampling.
result Consistent and efficient private inference method.
We develop a privatised stochastic variational inference method for Latent Dirichlet Allocation (LDA). The iterative nature of stochastic variational inference presents challenges: multiple iterations are required to obtain accurate posterior distributions, yet each iteration increases the amount of noise that must be …
Paper proposes a federated learning method for quantile inference with local differential privacy.
problem Federated learning of quantile inference under local differential privacy constraints.
method Local stochastic gradient descent with randomized mechanism for privacy and efficiency.
result Asymptotic normality and functional central limit theorem for the proposed estimator.
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.
Model explanations can leak sensitive training data information, posing privacy risks.
problem Privacy risks of model explanations that expose training data information.
method Membership inference attacks on feature-based model explanations.
result Backpropagation-based explanations reveal statistical information about decision boundaries, leaking training data membership.
This work makes federated Bayesian learning differentially private.
problem Privacy concerns in federated learning with diverse data and computational constraints.
method Modified Partitioned Variational Inference (PVI) to ensure differential privacy.
result Moderately private logistic regression models can be learned in the federated setting with similar performance to non-privately trained models.
Noise-aware DP inference improves accuracy for complex models.
problem Inaccurate results and biases in DP inference for complex models.
method Noise-aware stochastic gradient variational inference.
result Accurate coverages and predictive probabilities for complex models.
New DP bootstrap method for statistical inference with improved privacy and accuracy.
problem Lack of general techniques for conducting statistical inference under differential privacy.
method DP bootstrap procedure to infer sampling distribution and construct confidence intervals.
result DP bootstrap estimates provide consistent point estimates and asymptotically valid standard CIs.
Survey on privacy issues in deep learning and proposed solutions.
problem Privacy concerns in deep learning models due to sensitive data.
method Review of existing privacy techniques and gaps in research.
result Identification of test-time inference privacy as a research gap.
Fairness in machine learning increases privacy risks, especially for underrepresented groups.
problem Privacy risks in fair machine learning models, particularly for underrepresented groups.
method Membership inference attacks to measure information leakage and analyze fairness vs. privacy trade-offs.
result Achieving fairness in machine learning models increases privacy risks, especially for underrepresented groups.
Study compares federated learning and coreset approaches for privacy in distributed machine learning.
problem Measuring privacy in distributed machine learning approaches.
method Comparison of federated learning and coreset approaches using membership inference attack.
result Federated learning offers better privacy than coreset, but with higher communication cost.
Paper improves privacy for language models against reconstruction attacks.
problem Reconstruction attacks can regenerate training data from language models.
method Uses Rényi differential privacy with optimized privacy budgets.
result Better privacy guarantees for extraction of rare secrets.
Deep RL policies can leak private information from trained policies.
problem Privacy leakage in deep reinforcement learning models.
method Environment dynamics search via genetic algorithm and candidate inference based on shadow policies.
result 95.83% average recovery rate of floor plans from trained Grid World navigation DRL agents.
Proposes privacy-preserving sensor data transformations to prevent user re-identification and sensitive activity inference.
problem Privacy threats from shared sensor data and potential user re-identification.
method Mechanisms to transform sensor data to eliminate patterns for re-identification and sensitive activity inference, while maintaining minor utility loss.
result Reduced user re-identification accuracy to random guess level and prevented inference of sensitive activities.
Efficient method defends privacy in federated learning without accuracy loss.
problem Privacy attacks on federated learning by reconstructing and identifying local data.
method Random noise perturbation method that allows recovery of true gradients.
result Strong privacy protection without sacrificing learning accuracy.
This study examines how model architecture affects deep learning model privacy.
problem Privacy concerns in deep learning models due to potential leakage of sensitive information.
method Investigation of CNNs and Transformers, focusing on activation layers, stem layers, LN layers, and attention modules.
result Transformers generally exhibit higher vulnerability to privacy attacks than CNNs.
Paper explores differential privacy in high-dimensional federated learning, tackling server trustworthiness and estimation.
problem Maintaining privacy in distributed environments with high-dimensional data.
method Investigates scenarios with untrusted and trusted central servers, introduces novel federated estimation algorithms for linear regression models.
result Tight minimax rates depend on high-dimensionality even with sparsity assumptions, and novel algorithms handle slight variations among distributed models.
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.
Novel framework for privacy-preserving IPW methods in observational studies.
problem Estimating causal effects from observational studies while preserving privacy.
method Proposes a novel framework for privacy-preserving inverse probability weighting (PP-IPW) methods.
result Theoretical and empirical results support the effectiveness of PP-IPW methods.