Confidential Guardian prevents model abstention from being used to discriminate.
problem Dishonest institutions can exploit machine learning model abstention to unfairly deny services.
method Confidential Guardian uses zero-knowledge proofs to verify model confidence and detect suppression.
result Confidential Guardian effectively prevents the misuse of cautious predictions.
New attacks steal ML models via public APIs, even with confidence values.
problem Stealing confidential ML models via public APIs.
method Simple, efficient attacks that extract target ML models with near-perfect fidelity.
result Natural countermeasure of omitting confidence values from model outputs still admits harmful attacks.
Researchers develop attacks to steal machine learning hyperparameters.
problem Stealing confidential hyperparameters in machine learning models.
method Proposed attacks on various machine learning algorithms, evaluated both theoretically and empirically.
result Successfully steal hyperparameters from machine learning models.
Noise added to neural network features limits input reconstruction.
problem Protecting privacy during inference with deep neural networks.
method Hammersley-Chapman-Robbins bounds applied to noise added to neural network features.
result HCR bounds limit confidentiality but not accuracy.
Generative adversarial networks create synthetic insurance datasets from confidential originals.
problem Difficulty in accessing or sharing confidential insurance datasets for research.
method Design and use of three GAN architectures tailored for multi-categorical insurance data.
result MC-WGAN-GP synthesizes the best data, CTGAN is easiest to use, and MNCDP-GAN ensures differential privacy.
The paper shows how imitation learning can be exploited to extract DRL policies.
problem The confidentiality and integrity of DRL policies are vulnerable to model extraction attacks.
method Developed proof-of-concept attacks using imitation learning techniques.
result Demonstrated the feasibility of launching black-box attacks against DRL policies.
A new framework for private Bayesian tests maintains interpretability and computational efficiency.
problem Lack of interpretability and inability to quantify evidence in confidential data.
method Differentially private Bayesian tests based on test statistics.
result Established results on Bayes factor consistency under the proposed framework.
DeepGDL models create realistic power grids from confidential data.
problem Creating realistic power grids from confidential data.
method Graph distribution learning (GDL) with a deep nonlinear recurrent structure.
result DeepGDL models accurately create synthetic power grids.
We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish sharp upper and lower bounds on the convergence rates of statistical estimation procedures. As a consequence, we exhibit a precise tradeoff be…
Paper presents a lightweight, unobtrusive method to protect edge device data privacy.
problem Protecting inference data privacy in IoT edge devices with limited compute power.
method A lightweight neural network at edge devices to obfuscate inference data without indicating obfuscation.
result Effectively protects inference data confidentiality while preserving backend accuracy.
Protects proprietary policies from imitation learning by training adversarial policy ensembles.
problem Protecting policies from external observers cloning them.
method Introduces a reinforcement learning framework that trains an ensemble of near-optimal policies, making demonstrations useless for external observers.
result Demonstrates the existence of 'non-clonable' ensembles and provides a solution to the optimization problem.
New algorithms for clustering and synthetic data generation of heterogeneous tabular datasets.
problem Clustering and generating synthetic data from heterogeneous tabular datasets with hidden cluster structure.
method Developed MMM and MMMsynth algorithms for clustering and synthetic data generation.
result MMMsynth algorithm outperforms other literature tabular-data generators and approaches real data performance.
Survey of privacy-preserving distributed deep learning methods.
problem Protecting confidential patterns in data during distributed deep learning.
method Comparison of federated learning, split learning, large batch SGD, and privacy-preserving techniques.
result Trade-offs between computational resources, data leakage, and communication efficiency.
PHI Scrubber removes sensitive patient info from medical notes.
problem Protecting patient privacy in electronic health records.
method Deep learning model with de-convolutional neural network and bi-directional LSTM-CNN.
result Eliminates individually identifiable information from physician notes.
Study reveals the complex topology of real-world credit card transactions.
problem Understanding the true structure of real-world money flows from credit card data.
method Analysis of real-world credit card transaction data from a major bank, creation of a stochastic model.
result Real-world credit card transactions exhibit nontrivial characteristics in their topology.
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.
Decentralized LDA for privacy preserving topic modeling.
problem Learning topics from decentralized networks without sharing sensitive information.
method Adapted LDA model for decentralized optimization.
result Similar topic parameters and performance at each node as with stochastic methods.
Improved fraud detection in finance with quantum-enhanced federated learning.
problem Challenges in detecting financial fraud with traditional methods.
method Hybrid quantum-enhanced federated learning framework combining quantum LSTM with privacy-preserving techniques.
result Approximately 5% improvement in performance metrics compared to conventional models.
DeFi TrustBoost uses blockchain and AI to assess small business loans.
problem Assessing small business loans from low-wealth households.
method Combines blockchain and Explainable AI to ensure confidentiality, compliance, and security.
result Tamper-proof auditing and on-chain/off-chain data storage for financial organizations.
Missing data enhances privacy in differential privacy.
problem Privacy preservation in datasets with missing values.
method Formalized missing data as a privacy amplification mechanism within differential privacy.
result Incomplete data can yield privacy amplification for differentially private algorithms.
Proposes FMPCA for federated tensor data dimensionality reduction.
problem Integration of MPCA into federated learning.
method Federated Multilinear Principal Component Analysis (FMPCA).
result FMPCA preserves performance of traditional MPCA in federated learning.
FinDiff generates synthetic financial data for regulatory tasks.
problem Sharing microdata for research due to privacy regulations.
method Diffusion model using embedding encodings for mixed modality financial data.
result FinDiff excels in generating high-fidelity, privacy-preserving synthetic financial data.
Unified framework evaluates synthetic financial data models.
problem Data scarcity and confidentiality in finance hinder model development and testing.
method Multi-criteria evaluation of three generative paradigms: ARIMA-GARCH, VAEs, and TimeGAN.
result TimeGAN achieves the best balance between realism and temporal coherence.
Federated learning platform for drug discovery without sharing data.
problem Lack of secure collaboration in drug discovery.
method Industry-scale federated learning platform using cryptographic aggregation.
result Generated new scientific discoveries in drug discovery.
The paper analyzes a private likelihood-ratio test for frequency tables under differential privacy constraints.
problem Achieving privacy in statistical data analysis while maintaining statistical utility.
method A rigorous analysis of a private likelihood-ratio (LR) test for goodness-of-fit in frequency tables, considering (ε,δ)-differential privacy. result Characterization of the trade-off between differential privacy parameters (ε,δ) and statistical power of the private LR test. This paper improves federated learning for industrial predictive analytics by accommodating client heterogeneity.
problem Traditional federated models assume homogeneity in degradation processes, which doesn't apply to industrial settings.
method Personalized federated prognostic model using proximal gradient descent algorithm for joint parameter estimation.
result The proposed model enhances performance and provides comprehensive failure time distributions.
A new algorithm optimizes local objectives in federated learning with heterogeneous clients.
problem Optimizing local objectives in federated learning with heterogeneous client data.
method Proposes PF-PNE algorithm with double elimination strategy.
result PF-PNE algorithm optimizes local objectives with arbitrary heterogeneity and protects client data confidentiality.
SG-MCMC achieves strong differential privacy with simple modifications.
problem Balancing privacy and utility in machine learning models.
method Integrating SG-MCMC with differential privacy techniques.
result SG-MCMC achieves strong differential privacy with careful step sizes.
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.
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.
A federated model predicts failures using multi-stream incomplete data.
problem Insufficient data for reliable prognostic models in multi-stream applications.
method Federated data fusion, multivariate functional principal component analysis, (log)-location-scale regression model, federated algorithm.
result Performance is as good as classic non-federated models and better than individual models.
New method recovers graph latent positions under edge differential privacy.
problem Recovering latent graph information from privatized graphs.
method Applying geometric insights to adjust statistical inference for privatized graphs.
result Achieves consistent recovery of latent positions under local edge differential privacy constraints.
Research evaluates model extraction attacks on complex ML models and introduces a defense.
problem Model extraction attacks steal functionality of ML models through prediction APIs.
method Evaluation of Knockoff nets and introduction of a defense.
result Realistic adversaries can effectively steal complex ML models and evade known defenses.
Graph neural networks integrate causal knowledge for more accurate uplift modeling.
problem Identifying the most effective treatments and clients for marketing interventions.
method Combining graph neural networks with causal knowledge to estimate uplift values.
result The proposed method outperforms traditional approaches in predicting uplift values with minimal errors.
Federated learning leaks participant dataset quality even with secure aggregation.
problem Leakage of participant dataset quality in federated learning with secure aggregation.
method Image recognition experiments to infer and attribute dataset quality.
result Relative quality ordering of participants can be inferred and used for various purposes.
Paper proposes a GAN-based approach for RTLMP prediction.
problem Predicting real-time locational marginal prices (RTLMPs) in power markets.
method GAN-based video prediction model for spatio-temporal correlations.
result Proposed method accurately predicts RTLMPs without confidential information.
Multi-party machine learning leaks global dataset properties even with black-box access.
problem Leakage of global dataset properties in multi-party machine learning.
method Demonstrated leakage of sensitive attribute distributions in pooled data.
result A curious party can infer sensitive attribute distributions in other parties' data with high accuracy.
Optimal sampling strategy improves prediction accuracy with surrogate variables under measurement constraints.
problem Measurement-constrained datasets and lack of labeled data.
method A-optimality criterion for optimal sampling, leveraging surrogate variables.
result Achieves lower asymptotic variance and reduced empirical mean squared error.
Bayesian Optimization improves machine learning for detecting network attacks.
problem Detecting network attacks to secure critical information.
method Bayesian Optimization for tuning machine learning algorithms (SVM-RBF, RF, k-NN).
result The proposed framework achieves high accuracy and low false alarms.
Framework extracts deep neural networks from public data.
problem Extracting deep neural networks from black-box models.
method Active learning and large public datasets.
result Improved performance over uniform noise baseline.
The paper discusses fairness in bank stress tests, comparing various methods to address institutional differences.
problem Fair aggregation of bank-specific stress test models into a common model.
method Comparing various notions of regression fairness, including estimating and discarding centered bank fixed effects.
result The method of estimating and discarding centered bank fixed effects is preferable for linear models, improving forecast accuracy and equal treatment.
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.
Unified approach improves accuracy in private estimation.
problem Protecting sensitive information in statistical estimation.
method Unified Bayes Private Point (UBaPP) approach to Bayes point estimation under differential privacy constraints.
result Achieves better accuracy-privacy trade-off than traditional methods.
Cryptotree enables accurate predictions on encrypted data using Random Forests.
problem Applying machine learning to private data while preserving confidentiality.
method Adapting Neural RF to CKKS scheme for HE operations on encrypted data.
result Cryptotree achieves better prediction results on encrypted data than regular RF.
Paper proposes DPN for encrypted speech recognition, maintaining privacy and security.
problem Privacy and security issues in cloud-based speech recognition.
method Deep Polynomial Network (DPN) for encrypted speech, cloud-local joint decoding.
result DPN can make frame-level predictions over encrypted speech and return them in encrypted form.
Framework for pricing data products in data-poor markets.
problem Challenges in pricing advanced data products due to lack of transaction data.
method Prior-predictive Monte Carlo framework for generating probabilistic price bands.
result Stable probabilistic price bands for data products in data-poor markets.
This study tackles Gaussian process regression with summarized data.
problem Learning and inference with summarized data (summary statistics, counts) in spatial modeling.
method Sample quasi-likelihood approach to Gaussian process regression.
result Approximation performance of the method is influenced by data granularity and covariance function length scale.
HCFContext predicts mobile context using collaborative filtering and homomorphic encryption.
problem Accurate mobile context determination for enterprise policies.
method Proposes HPContext and HCFContext models using sequential history and collaborative filtering, with privacy-preserving homomorphic encryption.
result HCFContext enhances context prediction by leveraging related users' observations.