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.
Analysis of model updates reveals sensitive data leaks.
problem Information leakage during model updates.
method Differential analysis of language model snapshots.
result New metrics (differential score, differential rank) reveal sensitive data leaks.
Pruning neural networks adds differential privacy noise, preserving data utility.
problem Achieving differential privacy in neural networks without sacrificing data utility.
method Proving equivalence between pruning and adding differential privacy noise to hidden-layer activations.
result Pruning can be a more effective alternative to adding differential privacy noise for neural networks.
We study Eγ-divergence contraction and its privacy implications.
problem Analyzing privacy in data processing and algorithms.
method Generalizing Dobrushin's coefficient to Eγ-divergence and deriving contraction coefficients. result Local differential privacy can be expressed in terms of Eγ-divergence contraction, leading to precise sample size reductions. New method reconstructs significant parts of training data from neural networks.
problem Understanding and reconstructing training data from neural networks.
method Proposes a novel reconstruction scheme based on recent theoretical results about neural network training.
result Shows that a significant fraction of training data can be reconstructed from neural network parameters.
Introduces data ethics for mathematicians, covering background, open data, and privacy.
problem Ensuring ethical use of data in mathematical research and education.
method Overview of data ethics concepts, societal context, and resources.
result Highlights the importance of ethical considerations in data use.
Hybrid approach protects privacy while analyzing smart meter data.
problem Privacy concerns in AMI data analysis under CPUC regulations.
method Anonymization, differential privacy, federated learning, synthetic data, cryptography.
result Comprehensive privacy-preserving analytics framework for AMI data.
AI enhances financial forecasting with challenges in regulation and privacy.
problem Challenges in integrating AI with financial services and regulations.
method Integration of AI technologies like deep learning and reinforcement learning.
result AI improves financial forecasting but faces regulatory and privacy issues.
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.
Novel algorithm reduces privacy noise in machine learning.
problem High privacy noise in machine learning algorithms.
method Robust statistics, specifically median and trimmed mean, to bound sensitivity of SGD iterates.
result Improved privacy-utility trade-off with reduced noise and computational efficiency.
Paper addresses DP in bandits, focusing on zCDP and providing private algorithms.
problem Privacy concerns in recommender systems using user-sensitive data.
method Formalizes and compares different DP adaptations to bandits, proposes private algorithms for various bandit settings.
result Private algorithms ensure negligible privacy costs compared to non-private regret.
Study improves privacy in cross-silo federated learning by personalizing data.
problem Privacy concerns in cross-silo federated learning.
method Introduced sample-level differential privacy for silos, analyzed mean-regularized multi-task learning.
result Mean-regularized multi-task learning is a strong baseline for cross-silo federated learning under stronger privacy requirements.
Privacy-preserving SGD with heavy-tailed noise achieves differential privacy guarantees.
problem Privacy preservation in noisy SGD with heavy-tailed noise.
method Differential privacy guarantees for SGD with heavy-tailed noise.
result SGD with heavy-tailed perturbations achieves (0,O(1/n))-DP. Survey on threats to federated learning models.
problem Vulnerabilities in federated learning protocols.
method Taxonomy of threat models and attacks.
result Important future research directions.
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…
Enhances OTA FL algorithms by defining inverse feasibility for linear models.
problem Improving security and privacy in over-the-air federated learning.
method Defines inverse feasibility as an upper bound on condition number, analyzes existing model, proposes new model.
result Proposes a new OTA FL model with enhanced characteristics.
This work develops sampling methods for differential privacy using SHK geometry.
problem Approximating sampling for the exponential mechanism in differential privacy.
method Develops perturbation theory for SHK gradient flows and applies to differential privacy.
result Derives time-dependent Pure-DP guarantees and Approximate-DP certificates.
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…
This research develops heuristics to detect CoinJoin transactions on Bitcoin blockchain.
problem Compromised privacy in Bitcoin transactions due to CoinJoin.
method Analyzed open-source CoinJoin implementations to develop heuristics.
result Refined heuristics for identifying CoinJoin transactions on the blockchain.
In this paper, we consider the problem of preserving privacy in the online learning setting. We study the problem in the online convex programming (OCP) framework---a popular online learning setting with several interesting theoretical and practical implications---while using differential privacy as the formal privacy …
We study the relationship between the notions of differentially private learning and online learning in games. Several recent works have shown that differentially private learning implies online learning, but an open problem of Neel, Roth, and Wu \cite{NeelAaronRoth2018} asks whether this implication is {\it efficient}…
This paper recovers input data from transformer models using attention weights.
problem Recovering input data from transformer models for security and privacy concerns.
method Introducing an algorithm to minimize the loss function between expected and actual outputs of transformers.
result The algorithm successfully recovers input data from attention weights and outputs of transformers.
Privacy attacks reveal hidden information in network embeddings after node removal.
problem Privacy concerns in network embeddings after node deletion.
method Analyzed network embeddings and developed an attack to recover removed node information.
result Significant information about removed node's neighbors can be retrieved from remaining embeddings.
Protects user privacy in models using optional personal data.
problem Ensuring fairness for users who opt-out of data sharing.
method Formalizes protection requirements, introduces Protected User Consent (PUC), devises data augmentation strategy.
result PUC-compliant models can improve performance without disadvantaging opt-out users.
New attacks show ML models can be compromised even when targeting one concept.
problem Vulnerability of ML models to multi-concept attacks.
method Developed novel multi-concept attack techniques for deep learning.
result Successfully attacked one set of classifiers without impacting others.
Random projection (RP) is a classical technique for reducing storage and computational costs. We analyze RP-based approximations of convex programs, in which the original optimization problem is approximated by the solution of a lower-dimensional problem. Such dimensionality reduction is essential in computation-limite…
The paper provides Gaussian approximations for decentralized Federated Learning.
problem Lack of asymptotic statistical guarantees for local SGD in Federated Learning.
method Two generalized Gaussian approximation results for local SGD trajectories.
result Valid multiplier bootstrap procedures and Gaussian bootstrap-based tests for detecting adversarial attacks.
Deep Learning has recently become hugely popular in machine learning, providing significant improvements in classification accuracy in the presence of highly-structured and large databases. Researchers have also considered privacy implications of deep learning. Models are typically trained in a centralized manner with …
New findings on boosting sample complexity and implications for hardcore theorem.
problem Understanding the sample complexity of smooth boosting and its implications.
method Analyzing the sample complexity of smooth boosting and relating it to the hardcore theorem.
result The sample complexity of smooth boosting matches existing overhead and provides a separation from distribution-independent boosting.
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.
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 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.
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.
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.
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. Differential privacy is a statistical concept that can be explained through hypothesis testing.
problem Formalizing differential privacy as a statistical concept.
method Using David Blackwell's informativeness theorem, the paper shows differential privacy can be understood through hypothesis testing.
result The definition of f-differential privacy provides a unified framework for analyzing privacy bounds. A new method for tighter privacy loss accounting in adaptive analyses.
problem Ensuring individual privacy in adaptive analyses while staying within a privacy budget.
method A personalized privacy loss estimate and a Rényi differential privacy filter.
result Personalized privacy loss accounting can be practical and tighter than existing methods.
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.
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.
New findings show privacy affects generalization error in a non-monotonic way.
problem Privacy and robustness in distributed learning.
method Theoretical analysis and matching lower/upper bounds on algorithmic stability.
result Generalization error is non-monotonically affected by privacy, depending on noise level.
New privacy framework tailored to specific data distributions.
problem Protecting individual data points in decision-making processes.
method Introducing tangent differential privacy, a new form of differential privacy.
result Entropic regularization guarantees tangent differential privacy under general conditions.
Addresses theoretical and practical aspects of Gaussian differential privacy.
problem Theoretical and practical challenges in privacy-preserving data analysis.
method Discussion of f-differential privacy and Gaussian differential privacy.
result Gaussian differential privacy can enhance privacy in various applications.