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.
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.
Simpler, faster algorithm for uniformity testing in the shuffle model.
problem Testing uniformity of data in the shuffle model with privacy constraints.
method Simplified analysis and use of privacy amplification via shuffling.
result An algorithm with the same guarantees but simpler and more streamlined.
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.
Constructs models to meet any DP requirement without retraining.
problem Evolving privacy requirements at inference time.
method Two post-processing techniques: random selection and linear combination.
result Final private models satisfying any target privacy parameter.
Paper tackles federated learning with privacy, enhancing target data analysis.
problem Heterogeneity and privacy of distributed data in federated learning.
method Formulates federated differential privacy, studies statistical problems under privacy constraints.
result Federated differential privacy offers a balance between privacy and knowledge transfer.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.
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.
New federated f-differential privacy for collaborative learning.
problem Privacy in federated learning.
method Introducing federated f-differential privacy and proposing a generic private federated learning framework. result Proves federated f-differential privacy provides privacy guarantee on each record of one client's data. Introduces Relational Privacy (RP) to control relation memorization in question answering models.
problem Relation memorization in question answering models can lead to privacy issues.
method Formalizes Relational Privacy (RP) and Differential Relational Privacy (DrP), providing bounds on relation memorization.
result DrP allows effective learning of general properties of underlying concepts while preventing relation memorization.
DPNR preserves privacy of text representations using differential privacy.
problem Privacy leakage in deep learning text representations.
method DPNR uses Differential Privacy to provide formal privacy guarantees and dropout masking for enhanced privacy.
result DPNR reduces privacy leakage without significantly sacrificing main task performance.
DP-FedTabDiff generates private synthetic tabular data using diffusion models and differential privacy.
problem Privacy-preserving synthetic data generation for tabular data in regulated domains.
method Combines Differential Privacy, Federated Learning, and Denoising Diffusion Probabilistic Models.
result Achieves significant privacy improvements without compromising data quality.
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.
Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, ε, about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of ε in order to get acceptable utility of …
Differential privacy improves AI security, fairness, and learning.
problem Privacy violations, security issues, and model fairness in AI.
method Application of differential privacy in various AI areas.
result Differential privacy enhances AI performance in multiple areas.
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.
Tempered sigmoids improve deep learning privacy.
problem Privacy-preserving deep learning with strict differential privacy guarantees.
method Developed tempered sigmoid activation functions for deep learning models.
result Tempered sigmoids outperform ReLU in achieving state-of-the-art accuracy.
This paper improves privacy and fairness in federated learning by protecting sensitive data and ensuring group fairness.
problem Privacy and fairness issues in federated learning.
method Introduces group privacy through d-privacy, a localized form of differential privacy. result The method provides better group fairness than a global model in federated learning.
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.
Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presents a formal approach to carrying out privacy preserving text perturbation using the notion of dx-privacy designed to achieve geo-indistingui…
Paper evaluates and mitigates privacy risks in deep learning models.
problem Quantifying and defending against privacy attacks in deep learning.
method Quantitative evaluation of trade-offs, reformulating attacks, and proposing a novel SPN.
result Model accuracy improved by 5-20% while maintaining data privacy.
New algorithm maintains privacy while improving model performance in selective release.
problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.
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.
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.
Gradient sparsification enhances privacy-preserving machine learning models.
problem Improving performance of differentially-private machine learning models under privacy constraints.
method Gradient sparsification combined with compressed sensing and additive Laplace noise.
result Gradient sparsification can improve performance of differentially-private machine learning models for small privacy budgets.
New method reduces privacy impact on model accuracy for underrepresented groups.
problem Privacy mechanisms disproportionately affect underrepresented groups in machine learning models.
method Proposes DPSGD-F, a modified DPSGD that adjusts group contributions based on clipping bias.
result DPSGD-F removes disparate impact of differential privacy on model accuracy for protected groups.
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.
FLAME improves privacy in federated learning without trusted parties.
problem Ensuring privacy in federated learning without trusted parties.
method FLAME uses the shuffle model of differential privacy to achieve better accuracy and privacy.
result FLAME protocols improve testing accuracy by 60.7% compared to local model FL.
This paper presents a method to train a public model with private data using GANs and differential privacy.
problem Privacy concerns in training deep learning models on sensitive data.
method A three-player learning framework with differential privacy protection.
result The proposed method achieves a balance between privacy and model accuracy.
Asynchronous algorithms reduce privacy costs in distributed machine learning.
problem Privacy concerns in training machine learning models on scattered private data.
method Differentially-private asynchronous algorithms for collaborative training.
result Cost of privacy is inversely proportional to dataset size and privacy budgets.
Study on privacy-preserving health care models that sacrifice accuracy for data protection.
problem Privacy-preserving models in health care neglect data from the tails, reducing accuracy for small groups.
method Used state-of-the-art differentially private learning methods for clinical prediction tasks.
result Privacy-preserving models in health care exhibit steep tradeoffs between privacy and utility, and disproportionately influence large demographic groups.
Fine-tuning LLMs on privacy-sensitive data introduces privacy risk, and synthetic data audits can quantify this risk.
problem Fine-tuning LLMs on privacy-sensitive data introduces privacy risk.
method Generate synthetic canaries via high-temperature sampling from LLMs.
result Synthetic canaries are high-influence outliers that ensure strong audits.
PGFL framework learns personalized models with differential privacy.
problem Privacy-preserving personalized learning for diverse data.
method Exploits model similarities and differential privacy (zero-concentrated).
result Algorithm converges to optimal solutions with linear time complexity.
Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on specific data. As a result, achieving meaningful privacy guarantees in ML often excessively reduces accuracy. We propose Bayesian differential…
We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds. We adapt the Bayesian privacy accounting method to the federated sett…
This paper analyzes privacy threats in federated matrix factorization.
problem Privacy threats in federated matrix factorization models.
method Categorizes federated matrix factorization into three types and analyzes privacy threats.
result This is the first study of privacy threats in federated matrix factorization.
Data processing inequalities link Fisher information to local differential privacy constraints.
problem Understanding how Fisher information scales with local differential privacy constraints.
method Developed data processing inequalities for Fisher information under local differential privacy.
result Implications for private estimation with optimal bounds and error rates.
Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy. We introduce three tools to ma…
A privacy-preserving algorithm for high-dimensional bandits.
problem High-dimensional stochastic contextual linear bandits with sparse parameters under privacy constraints.
method PrivateLASSO algorithm based on sparse hard-thresholding and episodic thresholding.
result Minimax private lower bounds and utility guarantees for PrivateLASSO.
Structured subsampling improves privacy in deep time series forecasting.
problem Incompatible privacy guarantees with time series forecasting.
method Structured subsampling of sequential data for privacy amplification.
result Structured subsampling enables training with strong privacy guarantees.
Paper improves privacy-accuracy balance in federated learning.
problem Privacy-accuracy tradeoffs in federated learning.
method Personalized federated learning with joint differential privacy.
result Coordination of local and centralized learning improves accuracy while maintaining privacy.
Unified framework for subsampling mechanisms with tighter privacy guarantees.
problem Improving privacy in machine learning models through subsampling.
method Conditional optimal transport for deriving mechanism-specific subsampling guarantees.
result Tighter privacy bounds for subsampled mechanisms compared to traditional methods.
P3GM improves privacy-preserving data synthesis for high-dimensional data.
problem Mitigating privacy risks in releasing large volumes of sensitive data.
method Privacy-preserving phased generative model (P3GM) with two-phase learning process.
result P3GM significantly outperforms existing solutions in terms of noise reduction and data accuracy.
Privacy-preserving reinforcement learning from human feedback using decoupled reward modeling.
problem Training large language models with sensitive user information while preserving privacy.
method Proposes a privacy-preserving framework that imposes differential privacy on reward learning only.
result Privacy contributes an additional additive term to the suboptimality gap, and the upper bound is rate-optimal up to logarithmic factors.
Paper improves privacy bounds for shuffle model using novel numerical techniques.
problem Improving privacy guarantees in the shuffle model of differential privacy.
method Develops and evaluates numerical techniques for tighter (ε,δ)-differential privacy bounds. result Accurately evaluates privacy loss distribution for adaptive compositions of shufflers.
This paper quantifies privacy loss in exploratory data analysis.
problem Privacy loss in exploratory data analysis is often overlooked in privacy budgets.
method Quantitative analysis of privacy loss for statistical functions.
result Privacy loss must be considered in calculating machine learning privacy budgets.
This paper benchmarks privacy-preserving machine learning on medical images.
problem Ensuring privacy in medical image analysis while maintaining model accuracy.
method Comparing Local-DP and DP-SGD for differential privacy in medical imagery.
result Theoretical privacy guarantees do not fully align with real-world performance.
Paper explores how to design federated learning protocols that benefit all participants while maintaining privacy.
problem Privacy concerns undermine the accuracy benefits of federated learning in privacy-sensitive domains.
method The paper provides conditions for mutually beneficial federated learning protocols and designs protocols that maximize total utility and accuracy.
result The paper demonstrates that federated learning can be designed to be mutually beneficial, striking a balance between privacy and model accuracy.