This paper addresses privacy concerns in ratio statistics using differential privacy.
problem Privacy concerns in ratio statistics across machine learning areas.
method Develops a simple algorithm for differentially private ratio statistics, proving consistency and constructing confidence intervals.
result A simple algorithm can provide excellent privacy, sample accuracy, and bias properties in ratio statistics.
DiffSketch combines privacy and communication efficiency in distributed learning.
problem Privacy and communication efficiency in distributed machine learning.
method DiffSketch uses Count Sketch for data stream summarization to achieve both privacy and efficiency.
result DiffSketch provides strong differential privacy guarantees and significant communication compression.
This paper introduces differentially private permutation tests for hypothesis testing.
problem Privacy concerns in sensitive data analysis.
method Differentially private permutation tests for kernel methods.
result Proposes dpMMD and dpHSIC for two-sample and independence testing, achieving optimal power.
Dp-CLIP preserves privacy in multimodal AI training.
problem Privacy concerns in multimodal AI, especially in vision-language tasks.
method Differentially private adaptation of CLIP model.
result Dp-CLIP retains accuracy while ensuring privacy.
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.
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.
Study on protecting sensitive properties of datasets during analysis.
problem Ensuring privacy of sensitive properties in datasets.
method Proposes definitions and mechanisms for attribute privacy using the Pufferfish framework.
result Developed efficient and inefficient mechanisms for attribute privacy.
Alternating Direction Method of Multipliers (ADMM) is a widely used tool for machine learning in distributed settings, where a machine learning model is trained over distributed data sources through an interactive process of local computation and message passing. Such an iterative process could cause privacy concerns o…
We consider the problem of fitting a linear model to data held by individuals who are concerned about their privacy. Incentivizing most players to truthfully report their data to the analyst constrains our design to mechanisms that provide a privacy guarantee to the participants; we use differential privacy to model in…
Paper proposes a secure protocol for federated learning.
problem Combining robustness, privacy, and security in federated learning.
method Secure two-server protocol for federated learning.
result Offers both input privacy and Byzantine-robustness.
Hypothesis testing plays a central role in statistical inference, and is used in many settings where privacy concerns are paramount. This work answers a basic question about privately testing simple hypotheses: given two distributions P and Q, and a privacy level ε, how many i.i.d. samples are needed to…
Novel PP-ADMM and IPP-ADMM algorithms improve differential privacy in distributed machine learning.
problem Privacy concerns in ADMM-based distributed machine learning.
method Proposes PP-ADMM and IPP-ADMM algorithms to provide differential privacy while improving model accuracy and convergence.
result The proposed algorithms achieve better model accuracy and convergence under the same privacy guarantee.
The paper proposes differentially private sliced inverse regression algorithms for high-dimensional data.
problem Privacy concerns in high-dimensional data analysis.
method Differentially private sliced inverse regression algorithms designed for privacy preservation.
result Achieves minimax lower bounds up to logarithmic factors.
Paper discusses privacy issues in IoT and proposes a lightweight neural network approach.
problem Privacy concerns in IoT due to extensive data collection and processing.
method Developed a privacy-preserving inference approach for IoT objects and a deep neural network in the cloud.
result Satisfactory performance of the proposed approach on the MNIST dataset.
The rapid adoption of machine learning has increased concerns about the privacy implications of machine learning models trained on sensitive data, such as medical records or other personal information. To address those concerns, one promising approach is Private Aggregation of Teacher Ensembles, or PATE, which transfer…
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.
Proposes differentially private normalizing flows for privacy-preserving density estimation.
problem Privacy concerns in density estimation models when individuals are directly associated with the training data.
method Uses normalizing flow models with explicit differential privacy guarantees.
result Substantially outperforms previous state-of-the-art approaches in privacy-preserving density estimation.
Paper presents a privacy-preserving method for dynamic assortment selection.
problem Personalized assortment recommendations with data privacy concerns.
method Perturbed upper confidence bound method integrating calibrated noise.
result Policy satisfies Joint Differential Privacy (JDP) with near-optimal regret bound.
Paper studies optimal federated learning for nonparametric regression with privacy constraints.
problem Federated learning for nonparametric regression with heterogeneous differential privacy constraints.
method Proposes distributed privacy-preserving estimators and investigates their risk properties.
result Establishes matching minimax lower bounds for global and pointwise estimation.
Significant success has been realized recently on applying machine learning to real-world applications. There have also been corresponding concerns on the privacy of training data, which relates to data security and confidentiality issues. Differential privacy provides a principled and rigorous privacy guarantee on mac…
Proposes first privacy-preserving method for estimating Hawkes processes.
problem Estimating point process models with sensitive personal data raises privacy concerns.
method Proposes differential privacy for event stream data and two optimization algorithms.
result Efficiently estimates Hawkes process models with privacy and utility guarantees.
New privacy-preserving learning model for mixtures of private and public data.
problem Learning from datasets with both private and public data, where privacy concerns differ.
method Designing a differential privacy-preserving learning algorithm for a mixture of private and public sub-populations.
result Linear classifiers can be learned with sample complexity comparable to non-private PAC-learning, even when privacy status correlates with labels.
Our work investigates how to identify privacy violations in models using finite adversaries.
problem Identifying privacy violations in models with limited adversary capabilities.
method Investigates requirements for finite adversaries to identify privacy violations.
result Parameters quantify the capabilities of finite adversaries.
New privacy method for eye tracking data reduces correlations and maintains accuracy.
problem Privacy concerns in eye tracking data from VR/AR glasses.
method Transform-coding based differential privacy mechanism for eye movement data.
result Significant reductions in sample correlations and query sensitivities, providing high privacy without loss in accuracy.
Proposes a privacy-preserving method for survival function estimation.
problem Privacy leakage in survival function estimation using sensitive data.
method Differential privacy framework applied to Kaplan-Meier estimator and related metrics.
result The method provides utility and strong privacy guarantees with real-world data.
Paper protects privacy and fairness in deep learning models.
problem Ensuring fairness in deep learning models while protecting sensitive data.
method Uses differential privacy and Lagrangian duality to design fair predictors.
result Demonstrates improved model performance on prediction tasks.
Language models learn from training data and can leak private information.
problem Language models lack context understanding and can expose private data.
method Discussing the limitations of current privacy protection methods for language models.
result Existing privacy protection methods are insufficient for language models.
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.
Synthetic tabular data improves privacy while maintaining model performance.
problem Protecting privacy in synthetic data generation for machine learning.
method Deep generative models for tabular data, emphasizing privacy and model performance.
result Deep generative models enhance synthetic data generation for tabular datasets.
The paper explores the incompatibility between fair privacy, need-to-know, and fairness in classifier outputs.
problem The interaction between fair privacy, need-to-know, and fairness in classifier outputs.
method Formulated and explored the interaction between fair privacy, need-to-know, and fairness in classifier outputs.
result Optimal classifiers are generally incompatible with fair privacy and need-to-know.
Improved DP models with active learning on public data.
problem Differentially private models trained on sensitive data degrade performance.
method Fine-tuning DP models through active learning on public data.
result Improved accuracy for DP models while maintaining privacy guarantees.
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this paper, we introduce an efficient algorithm to address the above problem in a fully…
Distributed stochastic gradient descent is an important subroutine in distributed learning. A setting of particular interest is when the clients are mobile devices, where two important concerns are communication efficiency and the privacy of the clients. Several recent works have focused on reducing the communication c…
Paper introduces privacy-preserving few-shot learning for images.
problem Privacy risk in few-shot learning systems.
method Discrete embedding vectors and one-way hash functions.
result Achieves computational pan privacy without storing embeddings.
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.
This paper surveys differential privacy methods for transportation spatiotemporal data.
problem Protecting user privacy in public release of spatiotemporal data.
method Review of differential privacy mechanisms and their application in transportation.
result Challenges in deploying and adopting differential privacy in transportation.
Survey combines FL and control for better adaptability and privacy.
problem Combining FL and control for better adaptability and privacy.
method Combining Federated Learning (FL) and control methods.
result Combining FL and control enhances adaptability, scalability, generalization, and privacy.
Privacy-preserving boosting algorithm for machine learning.
problem Privacy concerns in machine learning with sensitive data.
method Local Differential Privacy to protect data privacy while boosting.
result Effective privacy-preserving boosting algorithm developed.
Paper proposes a privacy-preserving DML framework using local randomization and ADMM perturbation.
problem Privacy concerns in distributed machine learning with sensitive user data.
method Local randomization and ADMM perturbation to provide differential privacy and heterogeneous privacy levels.
result The framework minimizes privacy losses and maintains model generalization.
A novel approach to federated learning with strong privacy guarantees.
problem Maintaining privacy of clients' data and federator's objective in federated learning.
method Inspired by knowledge distillation and private information retrieval, the approach combines secret-sharing-based multi-party computation and graph-based private information retrieval.
result Strong information-theoretic privacy guarantees for federated learning.
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.
Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.
problem Lack of formal proofs of privacy in PP-GANs for image sanitization.
method Subverted PP-GANs for facial expression recognition to hide sensitive data in sanitized images.
result It is possible to hide sensitive identification data in sanitized PP-GAN output images, even allowing reconstruction of entire input images.
Efficiently preserves privacy in logistic regression for IoT data.
problem Balancing data privacy and utility in collaborative learning.
method Matrix encryption approach for secure multi-party computation.
result Proposes a privacy-preserving logistic regression model with fast convergence.
Differentially-private FNAS protects privacy while collaboratively searching for neural architectures.
problem Collaborative neural architecture search with privacy concerns.
method Federated Neural Architecture Search (FNAS) with differential privacy (DP-FNAS).
result DP-FNAS can search for highly-performant neural architectures while protecting individual parties' privacy.
Deep learning with medical data often requires larger samples sizes than are available at single providers. While data sharing among institutions is desirable to train more accurate and sophisticated models, it can lead to severe privacy concerns due the sensitive nature of the data. This problem has motivated a number…
The paper analyzes the trade-off between privacy and model fitness in collaborative machine learning.
problem Balancing privacy and model utility in collaborative machine learning.
method Differential privacy applied to noisy gradients in stochastic gradient descent.
result The fitness of the model is inversely proportional to the size of the datasets and privacy budget.
DPLP predicts links while protecting some node-pairs' privacy.
problem Link prediction with protected connections in private networks.
method DPLP uses differential privacy on graphs to protect node-pairs, applying a monotone transform and noise to base scores.
result DPLP effectively balances privacy and link prediction accuracy.
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.